docs-from-prs

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 inspects merged PRs via GitHub CLI (e.g., "gh pr list --repo ... --json number,title,mergedAt,body,files" in SKILL.md Step 1), which are user-generated, potentially public third-party contents that the agent is expected to read and act on (update docs/commit), so untrusted PR bodies could influence tool actions.