
Vigil
AI harness for long-running code audits, web pentests, and bug bounty hunting, built around how real investigations fail: anchored hypotheses, false…
ai-securitycode-analysisexploitation+9
31

AI harness for long-running code audits, web pentests, and bug bounty hunting, built around how real investigations fail: anchored hypotheses, false…

Fix-Like Artifacts With Embedded Defects

a guard that blocks catastrophic agent actions

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

AI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.

Replication package studying how LLM vulnerability auditors defer to static-analysis evidence, with a tree-sitter C/C++ front end, controlled…