gh-work-report

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 2 and reference.md) uses the gh CLI (gh api / graphql and gh search) to fetch repository metadata, PRs, issues and README/PR descriptions from GitHub and explicitly instructs the agent to read PR titles/descriptions and repo READMEs to synthesize themes and usage examples, which are untrusted, user-generated third‑party contents that can materially influence analysis and follow-up actions.