github

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md instructs using the gh CLI (e.g., gh pr, gh run view, gh api) to fetch PRs, issues, and CI logs from GitHub — public, user-generated content that the agent is expected to read and could materially influence actions — so it exposes the agent to untrusted third-party content.