react-doctor

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

• Third-party content exposure detected (high risk: 0.80). The UPSTREAM.md workflow explicitly instructs cloning and reading the public upstream repository at https://github.com/millionco/react-doctor (via npm run sync:upstream and "Read cloned files"), meaning the skill ingests open/public third‑party content that the agent is expected to interpret and integrate into skill updates, which could change behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's Quick Start runs remote code at runtime via "npx -y react-doctor@latest" (the package/source is https://github.com/millionco/react-doctor), so it fetches and executes external code that the skill relies on.