* feat: add Trojan Skill Hunter agent for auditing AI customization contributions
Adds a new agent that audits .agent.md, SKILL.md, .instructions.md,
hooks.json, and MCP/plugin manifests for hidden prompt injection, MCP-style
tool poisoning/shadowing, unicode steganography, excessive-agency scope
mismatches, and rug-pull/supply-chain drift before contributions are
merged, installed, or trusted.
Mapped to the OWASP Top 10 for LLM Applications (2025) and Invariant Labs'
MCP Tool Poisoning Attack research. Includes an explicit self-defense rule
so the agent treats reviewed content as untrusted data, never instructions
to obey.
* fix: reword attack-pattern examples to avoid PR risk-scan false positives
The Rule Zero bullet and two rug-pull/unpinned-fetch examples quoted the
exact literal phrases (e.g. 'ignore previous instructions', 'curl | bash')
that the repo's automated PR Risk Scan greps for. Reworded to convey the
identical meaning without the literal trigger strings - confirmed locally
with 'node eng/pr-risk-scan.mjs' (0 high/medium/info findings, was 3 high).
---------
Co-authored-by: Shubham Jiyani <shubham.jiyani@atqor.com>
Shubham Jiyani