describe-pr-nt

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads GitHub PR content (e.g., "gh pr diff {number}" and "gh pr view {number} --json commits") — user-generated, third-party PR diffs/commit messages are ingested and directly drive the agent's analysis and edits, so untrusted content could inject instructions into the workflow.