git-workflows

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

• Third-party content exposure detected (high risk: 0.90). The skill's github_workflow_fix workflow (references/source-commands.md: "github_workflow_fix.md", Steps 1–2) instructs the agent to call gh run list and gh run view --log-failed to fetch and interpret GitHub run summaries and logs (public, user-generated content) and then decide and perform fixes/PRs based on that evidence, which clearly ingests untrusted third-party content that can influence actions.