XBOW
Named by 31 kept items in this workspace.
20 items name it under tools, 10 under classification.technologies and 1 under classification.key entities.
Search every workspace for XBOW. It matches the name as written, so it can find other things that share it.
The items that name it 31
researchers who detailed the Chrome full-chain exploit; $250,000 bounty from Google; $40,000 compute cost
Offensive AI system whose researchers built a Chrome full-chain exploit in six days for $40k in API costs using GPT-5.6 Sol, earning a $250,000 Chrome full-chain reward.
agentic IDOR finder; agents log in as each role and map permissions before testing
Autonomous AI security research system that performed threat modeling, code auditing, vulnerability discovery, validation, and exploit development for CVE-2026-72018.
Prior art / inspiration: validated, safe-PoC findings and public challenge benchmark; source of 'prove it or drop it' discipline
Autonomous offensive security platform that discovers vulnerabilities at scale across applications and now de-duplicates findings before reporting them to customers.
Autonomous AI pentesting platform using separate attacking agents and independent validators to confirm vulnerabilities safely, with external safety model, scope-enforcing proxy, and auditability
Autonomous AI offensive security research system that discovered and validated the three Microsoft Critical RCEs described, including forming hypotheses, running proof commands, and using out-of-band callbacks; listed by Microsoft as finder and the first AI in its top-10 bug bounty leaderboard.
Autonomous offensive-security platform that orchestrates AI agents to find vulnerabilities under command-safety controls
AI-driven penetration testing platform for running governed, validated AI pentesting across complex application environments
Commercial AI-driven penetration testing product/benchmark reference, part of 2026 commercialization trend
AI-powered offensive security agent platform used to evaluate models by running them against real vulnerable applications to discover and exploit vulnerabilities
Security company/platform that benchmarks AI models on vulnerability-solving and maintains a fleet of models for different offensive security tasks (exploit crafting, validation, reconnaissance)
Closed, hosted SaaS AI pentesting tool cited as proving AI can top bug-bounty leaderboards; compared against as a single-agent, closed alternative
Autonomous pentester that finds IDORs (insecure direct object references) and other authorization/design flaws by exploring applications with multiple role-based accounts to learn expected access patterns before validating findings
Independent security platform/benchmark for web exploits; reported Mythos Preview as a 'significant step up over all existing models' with 'absolutely unprecedented precision'.
Tool referenced in Doyensec's comparison study against which Shannon's results on Photoview 2.4.0 were separately evaluated
AI-driven/autonomous penetration testing platform combining autonomous exploration with validated findings, controlled scope, and governance-ready reporting
Product/platform being built by the author's organization for finding and detecting vulnerabilities in native code; used to discover CVE-2026-45185
Autonomous offensive security (AI-led pentesting) platform used to discover IDOR and other business-logic vulnerabilities
All technologies in this workspace.