github-community-health

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 explicitly instructs the agent to fetch and read public, user-authored content (e.g., via multiple gh api calls like repos/{owner}/{repo}/community/profile, gitignore/licenses/templates and by reading repo files, plus curl to https://www.contributor-covenant.org/version/3/0/code_of_conduct.md), so untrusted third-party content is ingested and used to drive decisions and actions.