http-endpoints

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

• Third-party content exposure detected (medium risk: 0.30). The skill describes building HTTP endpoints and webhook receivers that process incoming HTTP requests containing outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching documentation from https://utilities.val.run/docs.md at runtime to obtain API details, introducing an unverifiable third-party dependency.