skill-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and verifies content from open public sources (Phase 3: "Official Documentation Verification" — e.g., "Use Context7 to fetch: /websites/", "Fetch: https://", GitHub commits/production repo searches and npm registry checks), so the agent will read and interpret untrusted third-party web content as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly describes runtime fetching of external docs via WebFetch/Context7 to verify API patterns and drive automated fixes (e.g., https://better-auth.com/docs/integrations/drizzle), so external content fetched at runtime can directly influence agent prompts/decisions and the skill depends on those live docs.