skill-builder

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses skill-seekers to clone and scrape GitHub repositories and external websites, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The configuration instructs fetching a remote setup script via curl from raw.githubusercontent.com during installation, which constitutes a weak/unknown/suspicious operational external dependency.