🧰 Gemini CLI

The items that name it 34

• StepSecurity Now Inventories AI Agent Skills in Your GitHub Repositories and on Developer Machines
  articleas affected products2026-10-08

  AI coding agent covered by StepSecurity's agent skills inventory; targeted in the Miasma worm payload.

• 3 lessons from frontier AI vulnerability research
  writeupas affected products2026-10-07
• Top AI Coding Agent Security Resources — October 2026
  articleas affected products2026-10-02It is written here as Gemini CLI (Google).

  Google

• https://github.com/dmdhrumilmistry/security-harness
  repoas classification.technologies2026-09-29
• Package Manager Sandboxing (Andrew Nesbitt)
  articleas tools2026-09-24It is written here as Gemini CLI (Seatbelt profiles or container).

  Seatbelt profiles or container

• Top 10 attacks on Claude Code and what each one actually broke
  writeupas affected products2026-09-23

  Affected by Miasma worm's config injection and by TrustFall's MCP server trust-prompt exploit; also tested in ToolLeak red team.

• leepokai/jev-guard
  toolas affected products2026-09-17It is written here as Gemini CLI (supported agent; no ask in BeforeTool).

  supported agent; no ask in BeforeTool

• WordPress Security Skills
  repoas tools2026-09-15

  AI coding agent supported for use with the skills

• What is an agent harness (and how do you secure one)?
  articleas affected products2026-09-14

  AI coding agent harness; tested in TrustFall; GitHub tokens/API keys stripped from child processes but remained readable in parent process where injected instructions run (Novee Security, Black Hat USA 2026)

• Top AI coding agent security resources — September 2026
  articleas affected products2026-09-03

  Tool-restriction annotation not enforced at runtime; secret stripping defeated via reading /proc/$PPID/environ in a shared PID namespace; Google rated the issue CVSS 10.0; also exploitable in 95.5% of runs in the 2,826-file skill benchmark

• Claude Code & Gemini CLI: GitHub Issue → CI Secrets
  writeupas affected products2026-09-01
• Uber ADR (Agentic AI Detection and Response)
  repoas affected products2026-08-21

  session journals captured by ADR Sensor on macOS, Linux, and Windows, including tool results and nested subagent sessions

• Nine AI coding agent incidents that ended with deleted data
  writeupas tools2026-08-04

  Google's AI coding agent for terminal-based coding tasks

• Nomos
  repoas affected products2026-08-02

  Coding agent whose issue tracker is cited among sources of the recursive-deletion failure reports

• When the Guardrails Slip: The Case for Hook-Based Governance Across Agent Platforms | Blog | Endor Labs
  articleas affected products2026-07-31

  affected by cross-vendor prompt-injection attack (Comment and Control)

• The OpenAI and Hugging Face security incident: why AI agents need deterministic guardrails | Blog | Endor Labs
  articleas tools2026-07-31

  Coding agent cited as exposing agent hooks for intercepting actions.

• Top Agentic AI security resources — August 2026
  articleas affected products2026-07-31

  Target of ADI demonstrations; also included in the 'week of sandbox escapes' index

• AI Security Briefing
  articleas affected products2026-07-18

  hit by Adversa's TrustFall

• AI Security Briefing
  writeupas affected products2026-07-18

  Closed-source agent, out of scope for direct testing; cited as affected by the TrustFall finding

• AI Security Briefing
  articleas affected products2026-07-18

  AI system fooled in 2025 by Trail of Bits' image-downscaling prompt-injection technique

• AI Security Briefing
  articleas tools2026-07-18

  Google's CLI agent; affected in the 'Comment and Control' study leaking its own API keys

• Destructive Command Guard (dcg)
  repoas affected products2026-07-15

  Supported AI coding agent hook target

• HOL Guard
  repoas affected products2026-07-15
• awesome-ai-security-tools
  repoas affected products2026-07-11

  AI coding agent covered by SkillSpector and Skill-Inject

• Microsoft's durabletask PyPI Package Compromised in Supply Chain Attack
  writeupas affected products2026-06-09

  AI coding tool triggered via .gemini/settings.json to execute malicious payload on session start

• Miasma Worm Hits Microsoft Again: Azure Functions Action and 72 Other Repositories Disabled After Supply Chain Attack Targeting AI Coding Agents
  writeupas classification.technologies2026-06-09
• GenAI App Security Checklist
  repoas tools2026-05-13

  CLI used to run the scan prompt against a local codebase (gemini "$(curl -s .../prompt.md)")

• paralax/SeldomMonster
  repoas tools2026-05-12

  LLM CLI these MCP servers are built for, though should work with any LLM that supports MCP

• Pantheon-Security/medusa
  repoas affected products2026-05-10It is written here as Gemini CLI (GEMINI.md).

  GEMINI.md

• TrustFall: 1-click coding agent RCE in Claude, Cursor, Copilot
  writeupas tools2026-05-07

  Agentic coding CLI from Google; compared for MCP trust dialog behavior (enumerates MCP servers by name)

• alirezarezvani/claude-skills
  repoas classification.technologies
• Sandyaa — open-source autonomous code auditor that proves bugs with working exploit PoCs
  repoas tools

  optional alternative backend for some Sandyaa analysis phases; auto-detected via PATH and authentication, or via GEMINI_API_KEY to auto-resolve latest Gemini model tiers

• Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
  articleas classification.technologies
• Plugin4Shell - Zero Click RCE Vulnerability found in top 4 most popular coding agents, millions of agents affected
  writeupas affected products

  Affected by Plugin4Shell via a variant using --ref/FETCH_HEAD; Google has deprecated Gemini CLI and will not patch it, so every install stays vulnerable

In every workspace you can read 66