Writing

Writing

Notes on agent security, static analysis, and keeping the evidence.

What Pair Coding Actually Looks Like

A real Semgrep session with a human, an agent, and the evidence we kept — including the parts that went wrong.

  • pair-programming
  • ai
  • security
  • semgrep
  • static-analysis

Your Agent's Skills Are Code. Audit Them.

Introducing SkillTriage, a static security auditor for AI agent skills and Claude Code plugins, mapped to the OWASP Agentic Skills Top 10.

  • ai-agents
  • security
  • owasp
  • claude-code
  • static-analysis

Playing with AI Pentest Tools

A look at two open-source AI pentest frameworks, CAI and PentAGI — what each does well, and which trade-offs matter for CTFs, bug bounty, and pentesting.

  • ai-agents
  • security
  • pentesting
  • tooling