triage

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:29 and SKILL.md:27-30 require reading the issue/PR body, comments, labels, relationships, author, and dates (outsider-authored text from external issues/PRs) and then using that content to build the readiness brief, which would be ingested into the agent’s LLM context at runtime.