audit-docs

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md requires the agent to “run the checks with grep, file reads, and the forge CLI” and to “find its PR in the forge (gh pr list ...)” and “propose the row update” using PR/issue data; those forge/issue/PR bodies are outsider-authored free text that can be ingested into the LLM context at runtime.