triage

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read GitHub issues and comments (e.g., "gh issue view --comments" and "gh issue list ...") and to read .out-of-scope/*.md files as part of triage, meaning it ingests user-generated, potentially untrusted third-party content from the issue tracker that directly informs decisions and actions.