29 results for “OSI”

List Grid

What you seeeverything

Recent Oldest Added A–Z

All types694 Articles246 Papers149 Repos121 Write-ups85 Advisories29

More types6

Threads28 Tools19 Talks8 Other6 Videos2 Courses1

🚨 Advisories “OSI”Clear all

x.comadvisory🛡️ Security

S2W_DailyThreat (@S2W_DailyThreat) on X

S2W post on CVE-2026-97229, a CVSS 10.0 remote code execution flaw in the GitLab CE/EE CI/CD regex compiler, disclosed October 13, 2026. Insufficient regex validation plus an integer overflow during encoding conversion lets an attacker who can add CI/CD config use a malicious regex and a UTF-8 repository path to run commands as the git user. Affects self-managed 19.2 before 19.2.8, 19.3 before 19.3.5 and 19.4 before 19.4.2. Rapid7 published analysis and a public PoC exists, with no in-the-wild exploitation confirmed as of October 15. No workaround exists, so patch or restrict access to a management network or VPN.

GitLabCVSS

CVE-2026-97229Rapid7S2W+1

AppSec, DevSecOps· Added 17 Oct 2026, published 16 Oct 2026

orca.securityadvisory🛡️ Security

Critical GitLab RCE Lets Unauthenticated Attackers Execute Code on Servers (CVE-2026-97229)

Orca Security analysis of CVE-2026-97229, a CVSS 10.0 flaw in GitLab CE/EE. An integer overflow (CWE-190) in the CI/CD regular expression compiler gives memory corruption and code execution as the git user. It is triggered by a crafted regex in .gitlab-ci.yml combined with a UTF-8 repository path, with no authentication needed on instances that allow public project creation or self-registration. Lists affected branches (19.2 before 19.2.8, 19.3 before 19.3.5, 19.4 before 19.4.2), the absence of a workaround, interim mitigations, and a Rapid7 PoC against GitLab CE 19.4.1 with ASLR on. Notes a prior max-severity GitLab bug (CVE-2026-85706) was probed in the wild within hours and later added to CISA KEV.

GitLab

CVE-2026-97229CVE-2026-85706CWE-190+2

AppSec, DevSecOps· Published and added 14 Oct 2026

rapid7.comadvisory🛡️ Security

CVE-2026-97229: Critical Unauthenticated Remote Code Execution in GitLab

Rapid7 analysis of CVE-2026-97229, a CVSS 10.0 integer overflow (CWE-190) in the Onigmo regex compiler used by GitLab CE/EE's CI/CD regex handling. A crafted regex in a .gitlab-ci.yml passes validation as US-ASCII, then is recompiled for a UTF-8 repository path, producing invalid instructions that give code execution as the git user. Rapid7 reproduced it on GitLab CE 19.4.1 with ASLR (patched in 19.4.2); despite the vendor's "unauthenticated" rating, the attacker needs to commit a malicious config to a public project, which self-registration allows. No in-the-wild exploitation is confirmed, and Rapid7 recommends urgent upgrades.

GitLabRubyCVSS

CVE-2026-97229CWE-190Onigmo+1

AppSec, DevSecOps· Published and added 13 Oct 2026

github.comadvisory🧠 AI

MCP specification 2026-07-28 stable release

GitHub release announcing the stable 2026-07-28 revision of the Model Context Protocol specification, published from the modelcontextprotocol/modelcontextprotocol repository. The release page itself only points to the official MCP website for the spec and to a changelog for the detailed changes. It matters as the canonical version marker that MCP client, server and SDK implementers track for protocol changes.

Model Context ProtocolGitHub

mcp· Added 9 Oct 2026

github.comadvisory🛡️ Security

go-ethereum v1.17.8 "Protein Sludge Pack"

Security-focused release notes for go-ethereum (Geth) v1.17.8, patching several denial-of-service vulnerabilities in the eth/snap p2p protocol handlers, hardening JUMPDEST analysis caching against post-Amsterdam-fork attacks, requiring IP verification before accepting discovery statements, fixing a rogue-STUN-server crash, and closing a DoS vector tied to BAL accounts. Most issues only become exploitable after the Amsterdam fork activates, and the release also includes RPC correctness fixes (eth_simulateV1, eth_createAccessList) and a Sparse Blobpool (EIP-8070) correctness bug.

go-ethereumEthereum

Amsterdam forkEIP-8070

Blockchain· Added 8 Oct 2026

nvd.nist.govadvisory🛡️ Security

CVE-2026-57860: ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined i

CVE-2026-57860 describes an arbitrary code execution flaw in ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI that automatically loads and executes MCP servers defined in a repository's .mcp.json on startup without user confirmation. A malicious repo can define mcpServers entries with arbitrary command/args (e.g. bash -c) that spawn under the invoking user's privileges the moment forge is run inside the cloned repo, giving attackers a reliable initial-access and persistence primitive against developers evaluating untrusted code. CVSS 4.0 8.4 HIGH, CWE-829 (inclusion of functionality from untrusted control sphere); a fix commit and VulnCheck advisory are linked.

Model Context Protocol

CVE-2026-57860CWE-829

AI Security· Added 26 Sep 2026

nvd.nist.govadvisory🛡️ Security

CVE-2026-20685: An attacker in a privileged network position may be able to leak sensitive information

CVE-2026-20685 is a medium-severity (CVSS 6.5) path handling vulnerability in Apple's Private Cloud Compute (PCC), classified under CWE-20 and CWE-22, that could let an attacker in a privileged network position leak sensitive information. Apple addressed the issue with improved path validation, fixed in PCC Release 5E290.3.

Apple Private Cloud Compute

CVE-2026-20685CWE-20path traversal

AppSec· Added 26 Sep 2026

github.comadvisory🛡️ Security

Missing authentication on MCP HTTP endpoint allows unauthenticated privileged tool calls

GHSA advisory for jovancoding/network-ai disclosing that its MCP HTTP transport (bin/mcp-server.ts, lib/mcp-transport-sse.ts) accepts JSON-RPC tools/call requests with zero authentication, session, or origin checks, and binds to 0.0.0.0 by default. The PoC shows an unauthenticated attacker can enumerate 22 registered tools and invoke privileged ones - config_get/config_set to read and mutate live orchestrator configuration, agent_list/agent_spawn/agent_stop, token_create/token_revoke, budget_set_ceiling, and blackboard_write/delete - with curl requests against a local Docker deployment. Remediation recommended enforcing bearer-token auth in _handlePost() before dispatch, defaulting to 127.0.0.1 binding, and gating state-mutating tools behind authorization checks.

Model Context ProtocolDockerTypeScript+1

AI Security, AppSec· Added 26 Sep 2026

github.comadvisory🛡️ Security

CVE-2026-21852 - GitHub Advisory Database

GitHub advisory GHSA-jh7p-qr78-84p7 for Claude Code: a malicious repository could ship a project settings file setting ANTHROPIC_BASE_URL to an attacker-controlled endpoint. Claude Code made API requests during project load before the trust prompt was shown, leaking data including the user's Anthropic API key. Fixed in auto-updated versions; manual updaters should upgrade. It is CVSS v4 scored, with network attack vector and passive user interaction, and mapped to a credential-transmission weakness (insecure transmission/storage of credentials).

Claude CodeAnthropicCVSS+1

GHSA-jh7p-qr78-84p7ANTHROPIC_BASE_URLworkspace trust prompt bypass

AI Security, AppSec· Added 26 Sep 2026

github.comadvisory🛡️ Security

CVE-2026-44895 - GitHub Advisory Database

GitHub advisory for @yoda.digital/gitlab-mcp-server (mcp-gitlab-server): with USE_SSE=true the HTTP/SSE transport has no authentication, sends wildcard CORS headers, and binds to 0.0.0.0. Any network caller or any web page the operator visits can open /sse and POST /messages to drive all 86 GitLab tools (delete_repository, push_files, etc.) using the operator's personal access token. It includes a curl PoC, a CVSS 4.0 vector (~6.3 Medium, effectively High when SSE is enabled) and four fixes: required auth token, loopback bind, a CORS allowlist, and the OAuth roadmap.

Model Context ProtocolGitLabNode.js+2

CWE-306CVSS 4.0

AI Security, AppSec· Added 26 Sep 2026

orca.securityadvisory🛡️ Security

Breaking: GitLab Critical Path Traversal Flaw Exploited in the Wild — Patch Immediately

Details CVE-2026-85706 (CVSS 10.0), an unauthenticated arbitrary file read in GitLab CE/EE's repository commits API exploitable via a crafted file.path parameter in a single POST request, requiring only that one public project exist on the instance. It also covers CVE-2026-87719 (CVSS 9.9), an authenticated insecure deserialization bug in GitLab EE's GraphQL subscription serializer reachable via Duo Chat access that leaks stored Elasticsearch/OpenSearch credentials. Both affect GitLab versions through 19.3.1; CVE-2026-85706 is under active internet-wide scanning per WatchTowr Labs and is in CISA's KEV catalog with a federal patch deadline, with fixes in GitLab 19.1.8/19.2.6/19.3.2.

GitLabCVSSElasticsearch+1

CVE-2026-85706CVE-2026-87719CISA KEV+2

AppSec, Threat Intel· Published and added 14 Sep 2026

rapid7.comadvisory🛡️ Security

CVE-2026-85706: Critical GitLab Path Traversal Exploited in the Wild

GitLab patched CVE-2026-85706, a critical (CVSS 10.0) path traversal flaw (CWE-22) in the repository commits API that lets an unauthenticated attacker read arbitrary files from self-managed GitLab CE/EE instances; CISA added it to the KEV catalog on September 11, 2026 due to active exploitation, with a remediation deadline of September 14. The same patch release fixes CVE-2026-87719, a critical insecure deserialization bug (CWE-502) letting an authenticated Duo Chat user exfiltrate Advanced Search configs and credentials via a crafted GraphQL subscription argument, plus 17 other vulnerabilities. Rapid7 recommends emergency patching and post-patch compromise checks given confirmed in-the-wild exploitation.

GitLabCVSSGraphQL+1

CVE-2026-85706CVE-2026-87719CWE-22+1

AppSec, Threat Intel· Added 7 Oct 2026, published 14 Sep 2026

horizon3.aiadvisory🛡️ Security

CVE-2026-85706: GitLab CE/EE Repository Commits API Path Traversal

CVE-2026-85706 is a CVSS 10.0 critical path traversal vulnerability in GitLab CE/EE's repository commits API, caused by improper path confinement combined with missing authentication enforcement. It allows unauthenticated, remote attackers to read arbitrary files from the GitLab server — potentially exposing credentials, secrets, tokens, SSH keys, and database credentials. Affects versions 18.7 through 19.1.7, 19.2.0-19.2.5, and 19.3.0-19.3.1; fixed in 19.1.8, 19.2.6, and 19.3.2.

GitLabCVSS

CVE-2026-85706path traversal

AppSec· Added 17 Sep 2026, published 11 Sep 2026

watchtowr.comadvisory🛡️ Security

Rapid Reaction: GitLab Critical Path Traversal Vulnerability (CVE-2026-85706)

watchTowr's rapid-reaction analysis of CVE-2026-85706, a critical (CVSS 10.0) unauthenticated path traversal in GitLab CE/EE's repository commits API, patched in versions 19.3.2, 19.2.6, and 19.1.8. The flaw lets an unauthenticated attacker read arbitrary files (configs, secrets) from self-managed GitLab servers via crafted requests to /api/v4/projects/{id}/repository/commits/ with a file.path parameter; watchTowr reproduced the bug and reports honeypot probes indicating attackers have already reverse-engineered it ahead of mass exploitation.

GitLab

CVE-2026-85706path traversal

AppSec· Added 21 Sep 2026, published 11 Sep 2026

watchtowr.comadvisory🛡️ Security

Rapid Reaction: GitLab Path Traversal Vulnerability (CVE-2026-85706)

watchTowr's rapid-reaction analysis of CVE-2026-85706, a critical (CVSS 10.0) unauthenticated path traversal vulnerability in the GitLab CE/EE repository commits API, patched in versions 19.3.2, 19.2.6, and 19.1.8. The flaw allows an unauthenticated attacker to read arbitrary server-side files via the commits API due to improper path confinement and missing auth enforcement; watchTowr's honeypot network was already observing exploitation probes at time of publication. The post includes hunting guidance (searching logs for POST requests to /api/v4/projects/{id}/repository/commits/ containing file.path parameters) and patching priorities for self-managed instances.

GitLabCVSS

CVE-2026-85706

AppSec· Added 16 Sep 2026, published 11 Sep 2026

soliditylang.orgadvisory🛡️ Security

Solidity 0.8.37 Release Announcement

Solidity 0.8.37 release notes disclosing three EF bug-bounty-reported compiler bugs with security implications: deleting an element of a memory bytes array (or converted string) zeroed the full 32-byte word instead of one byte, corrupting adjacent data in the evmasm pipeline (all versions ≤0.8.36); a stack-to-memory spill-slot collision in mutually recursive functions under --via-ir silently overwrote live variables (0.7.2–0.8.36); and require() with a custom error using named arguments encoded parameters in call-site rather than declaration order, producing structurally valid but semantically wrong revert data. The release also adds two non-security miscompilation fixes, an experimental planning-based stack shuffler for the SSA CFG backend, support for the Amsterdam EVM's SLOTNUM opcode (EIP-7843), and removes/deprecates several experimental features.

SolidityEthereum

shaheenfazimNg Sze HonCantina Security+2

Blockchain· Added 29 Sep 2026, published 10 Sep 2026

securitylab.github.comadvisory🛡️ Security

GHSL-2026-203: Same-second TOCTOU in jupyterlab/maintainer-tools

GitHub Security Lab discloses GHSL-2026-203 / CVE-2026-84973, a same-second time-of-check-to-time-of-use race condition in the jupyterlab/maintainer-tools update-snapshots-checkout GitHub Action. The action compares one-second-precision pushed_at and comment created_at timestamps to detect post-authorization pushes, but a strict greater-than check lets an attacker push a malicious commit in the same second as an authorized "please update snapshots" comment, causing the action to check out and later execute attacker-controlled code (including a local composite action and jlpm-driven package scripts) with the workflow's GITHUB_TOKEN (contents: write, pull-requests: write) in the jupyter/notebook repository. The issue was fixed in v1.0.0 and is a variant of the "pwn request" class of GitHub Actions vulnerabilities.

GitHub ActionsGitHubjlpm+1

CVE-2026-84973GHSA-wwhg-p79f-vfvmCWE-367+4

DevSecOps, Supply Chain· Added 20 Sep 2026, published 4 Sep 2026

scworld.comadvisory🛡️ Security

Grafana fixes critical SSRF flaw affecting Grafana MCP servers

Grafana patched CVE-2026-19516 (CVSS 9.1), a critical SSRF in the Grafana MCP server's grafana_api_request tool where a caller-supplied X-Grafana-URL header could control the method, path and body of outbound requests, letting an attacker reach internal-only services from the server's network position. Pillar Security researchers chained this with a second flaw — the MCP server accepting unauthenticated "session-shaped IDs" it never issued — and demonstrated using it to hit the AWS IMDSv2 endpoint and retrieve cloud credentials via a two-step PUT/TTL token request. Grafana MCP v1.1.0 adds optional bearer-token auth to close the session-forgery gap; Pillar frames MCP servers broadly as "identity brokers" that need explicit outbound destination policies and mandatory auth for remote deployments.

GrafanaModel Context ProtocolAWS

CVE-2026-19516CVE-2026-15583Pillar Security+2

AppSec, AI Security, Identity & Access· Added 26 Sep 2026, published 3 Sep 2026

grafana.comadvisory🛡️ Security

Grafana MCP server-side request forgery via X-Grafana-URL header (grafana_api_request) | Grafana Labs

Grafana advisory for CVE-2026-19516, a critical (CVSS 9.1) SSRF in mcp-grafana. A caller able to invoke the grafana_api_request tool can set the X-Grafana-URL header to redirect outbound requests, choosing method, path and body, to internal, loopback and link-local services including cloud metadata endpoints, and read the responses. The earlier fix for CVE-2026-15583 only stopped the service-account token leaking to other destinations and did not restrict the destinations; the fix is in version 1.1.0 and later.

GrafanaModel Context ProtocolCVSS

CVE-2026-19516CVE-2026-15583SSRF+1

AppSec, AI Security· Added 12 Aug 2026

aws.amazon.comadvisory🛡️ Security

CVE-2026-18394 - Incorrect authorization in Strands Agents Tools http_request tool

AWS bulletin for CVE-2026-18394, an incorrect authorization flaw in the http_request tool of the open-source strands-agents-tools package used with the Strands Agents SDK. The tool exposed an LLM-controllable proxies parameter that let attacker-controlled web content (via indirect prompt injection) redirect requests through an actor's proxy while the hostname allowlist check still passed, disclosing HTTP_REQUEST_TOKEN_CONFIG-bound credentials in cleartext Authorization headers on the first hop. Fixed in version 0.8.2; AWS recommends upgrading and rotating any credentials configured on affected versions.

AWSStrands AgentsLLM

CVE-2026-18394

AI Security, AppSec· Added 6 Aug 2026

nvd.nist.govadvisory🛡️ Security

CVE-2026-59950

CVE-2026-59950 (CVSS 7.6) affects the MCP Python SDK's deprecated mcp.server.websocket.websocket_server transport, which accepted WebSocket handshakes without validating Host or Origin headers, giving no SDK-level way to restrict which origins could connect to applications exposing that transport. This is a classic CSWSH-style origin-validation flaw (CWE-346, CWE-1385) fixed in mcp 1.28.1.

Model Context ProtocolPython

CVE-2026-59950GHSA-vj7q-gjh5-988wCWE-346+1

AppSec· Published and added 17 Jul 2026

nvd.nist.govadvisory🛡️ Security

CVE-2026-55608

CVE-2026-55608 affects n8n-MCP, an MCP server exposing n8n node documentation and operations to AI assistants. Prior to version 2.57.4, when run in multi-tenant HTTP mode (ENABLE_MULTI_TENANT=true), an authenticated tenant could bypass tenant scoping and access or delete default-scope workflow_versions backups left over from earlier single-tenant deployments or migrations, exposing other tenants' workflow data. The issue is tracked as CWE-200 (information exposure) and CWE-863 (incorrect authorization) and is fixed in v2.57.4.

Model Context Protocoln8n

CVE-2026-55608CWE-200CWE-863

AppSec· Published and added 16 Jul 2026

advisories.gitlab.comadvisory🛡️ Security

AI Security Briefing

CVE-2026-52830 describes a path traversal flaw in fast-mcp-telegram, a PyPI package exposing Telegram as an MCP server, where HTTP Bearer tokens are joined directly into a session-file path without normalization. The verifier blocks the literal reserved token "telegram" but not path separators, so a token like "../fast-mcp-telegram/telegram" lets a remote HTTP client authenticate as the default legacy session, bypassing the control meant to keep multi-user HTTP sessions from colliding with the default stdio/legacy account. Account-prefixed MCP tool naming does not prevent the bypass since prefixed tools for the compromised default account remain accessible.

PyPITelegramModel Context Protocol+1

CVE-2026-52830path traversal

AppSec· Published and added 5 Jul 2026

stepsecurity.ioadvisory🛡️ Security

simonecorsi/mawesome GitHub Action has been compromised

StepSecurity reports that the simonecorsi/mawesome GitHub Action repository was compromised on June 24, 2026, when an attacker force-pushed malicious commits and repointed several release tags to point at them, so any workflow pinned to those tags subsequently ran the attacker's code inside its GitHub Actions runner. StepSecurity notes the attack method mirrors the codfish/semantic-release-action compromise disclosed the same day, suggesting a coordinated campaign targeting GitHub Action maintainers via tag hijacking.

GitHub Actions

simonecorsi/mawesomecodfish/semantic-release-action

Supply Chain, DevSecOps· Added 3 Sep 2026, published 1 Jul 2026

vulnerability.circl.luadvisory🛡️ Security

Vulnerability-Lookup

GHSA-73cv-556c-w3g6 (CVE-2026-49257, CWE-306) documents that mcp-pinot v3.0.1 and earlier defaults to an HTTP MCP server bound to 0.0.0.0:8080 with oauth_enabled=False, exposing all 14 tools — including read_query, create_schema and create_table_config — to any unauthenticated network caller. The server proxies calls using its own server-side Pinot credentials, creating a confused-deputy condition that grants full read/write access to the backing Apache Pinot cluster (CVSS 10.0). Fixed in v3.1.0 (PR #95) by defaulting the bind host to 127.0.0.1, refusing non-loopback exposure without OAuth, and gating Helm exposure behind OAuth.

Model Context ProtocolPythonPyPI+2

CVE-2026-49257CWE-306

AI Security, AppSec· Added 26 Sep 2026, published 18 Jun 2026

github.blogadvisory🛡️ Security

GitHub Repository Rulesets

GitHub changelog entry announcing two repository ruleset changes. Individual users can now be added as bypass actors on repository-level rulesets through the UI, REST API and GraphQL, so a dedicated team or role is no longer needed for a single person or service account. Repository admins can also rename a branch covered by an organization or enterprise ruleset, but only if the new name stays within the scope of every ruleset that applied to the old one. Otherwise the rename is blocked and an org or enterprise admin must do it, and org and enterprise admins can turn the capability off. This matters for branch-protection governance because bypass lists and rename rights affect who can circumvent required controls.

GitHubGraphQL

DevSecOps· Added 3 Sep 2026, published 11 May 2026

socket.devadvisory🛡️ Security

Socket: Critical vm2 Sandbox Escape

Socket disclosed that a critical sandbox escape in vm2 (GHSA-ffh4-j6h5-pg66, CVE-2026-26956), which lets attacker-controlled JavaScript passed to VM.run() escape isolation and execute arbitrary OS commands via WebAssembly.JSTag, affects far more than the officially listed vm2 3.10.4/Node 25 scope. Socket's testing showed 66 vm2 releases from 0.2.2 through 3.10.4 are exploitable on Node.js 24.15.0, and any Node runtime exposing WebAssembly.JSTag is vulnerable, meaning downstream SCA/scanner tools using the narrower advisory data would miss real exposure. Socket is releasing free Certified Patches (via `socket patch add`) for the issue alongside upgrade guidance to vm2 3.10.5+.

Node.jsSocket

CVE-2026-26956GHSA-ffh4-j6h5-pg66

Supply Chain, AppSec· Published and added 8 May 2026

vulnerablemcp.infoadvisory🛡️ Security

MCP TypeScript SDK Cross-Client Data Leak (CVE-2026-25536)

CVE-2026-25536 is a cross-client data leak in the official MCP TypeScript SDK (v1.10.0-1.25.3, CVSS 7.1): when a single McpServer instance reuses a StreamableHTTPServerTransport across multiple concurrent client connections, a race condition in the response multiplexing logic can route one client's tool results, resource content, or errors to a different client. This breaks tenant isolation in multi-user MCP server deployments, a common production pattern, potentially exposing sensitive API responses, file contents, or database query results across security boundaries. Fixed in SDK v1.26.0; recommended mitigations include upgrading, using per-client McpServer instances, and adding client-side response correlation checks.

Model Context ProtocolTypeScriptCVSS

CVE-2026-25536StreamableHTTPServerTransportMcpServer

AppSec· Added 30 Sep 2026, published 4 Feb 2026

sentinelone.comadvisory🛡️ Security

CVE-2026-21852 — Claude Code Information Disclosure (pre-trust config injection leaks API keys)

CVE-2026-21852 describes a flaw in Claude Code versions prior to 2.0.65 where a malicious repository's settings file can override ANTHROPIC_BASE_URL and have it applied during project load before the user sees or accepts the trust-confirmation prompt, causing the user's Anthropic API key to be sent to an attacker-controlled endpoint. The root cause is an initialization-order bug (CWE-522, insufficiently protected credentials) where untrusted repo config is parsed and acted on ahead of trust verification; Anthropic fixed it in 2.0.65 by moving trust checks before config processing. Mitigations include updating, rotating exposed keys, and avoiding opening unfamiliar repos until patched.

Claude CodeAnthropic

CVE-2026-21852CWE-522

AI Security, Identity & Access· Added 30 Sep 2026, published 21 Jan 2026