taste-skill

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches pictures and asset information from open collections over the network via an asset script.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of an external personal GitHub repository via npx skills add, introducing a third-party operational dependency with unknown publisher provenance under the high tier.