diagnose-workflow-failure

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses GitHub Actions job logs from third-party repositories using gh api and gh run view (see SKILL.md Step 1/Step 2), which are user-generated, untrusted content that the agent reads and uses to decide and perform fixes, creating a risk of indirect prompt injection.