theangry-ai-code-audit

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s required workflow is to “inspect changed files, surrounding source, repo instructions, tests and proof surfaces,” which at runtime will typically include outsider-authored text such as issue/PR discussion bodies or other contributors’ code/comments that the agent reads and feeds into the LLM context for review.