x-ray

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads a remote VERSION file from GitHub via curl and searches for spec/whitepaper documentation using glob patterns, but does not monitor or consume any outsider-authored free text feeds or queues.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill executes curl -sf https://raw.githubusercontent.com/pashov/skills/main/x-ray/VERSION at runtime to fetch the latest version information, creating an operational dependency on an external remote source.