runway

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches external documentation and API reference markdown from https://www.pixazo.ai/models/runway.md, which is a low-risk ingestion of third-party content fetched actively by URL.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external instructions and reference configuration from https://www.pixazo.ai/models/runway.md at runtime, constituting an operational dependency with unknown/weak provenance.