yak-shaving-triage

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill is a workflow for triaging side findings. Its only arguably concealing element is the instruction to run ordinary checks silently instead of reporting them, which hides some of its own activity from the user without any malicious aim, so it is at most medium under the recall-first override.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required reconciliation workflow searches the project's GitHub issues and reads related pull request contents, which outsiders can author or comment on, and this is a required step whenever search is eligible.