github-cli

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and read user-generated GitHub content (e.g., running gh pr view --json comments,reviews and gh api graphql to read PR review thread bodies from github.com), so untrusted third-party PR/issue comments are ingested and can influence actions.