analyze-dependencies

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 explicitly instructs running commands that query public package registries and vulnerability databases (e.g., "npm outdated", "npm audit", "pip audit") and to check open issues and PRs (step 8), which ingest user-generated, public web content (package metadata, advisories, GitHub issues/PRs) that can materially influence the audit's decisions.