github-scanning

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to search and fetch content from GitHub (issues, PRs, discussions, releases, workflow runs via github_list_releases and search queries), which is public, user-generated third-party content that the agent must read and use to drive triage, scoring, and follow-up actions.