ci-debug-workflow

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

• Third-party content exposure detected (high risk: 0.90). The workflow explicitly tells the agent to read CI logs and extract reproduction steps from external bug reports (see SKILL.md "Read CI logs first" and references/bug-thread-extraction.md which lists GitHub Issues and Slack/Discord threads), meaning it ingests untrusted, user-generated third‑party content that could contain instructions influencing actions.