gimbal-runs

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to run product validation workflows (gimbal run validate-product) that fetch external URLs and ingest potentially outsider-authored content during UI/UX testing suites.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references a public URL (https://router.diffusion.io/v1/models) in an example curl command used for model discovery at runtime, representing a common unofficial or external API dependency.