automation

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow includes webhook ingestion and third-party API connections where outsider-submitted webhook payloads and external API responses are parsed and processed.

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

• Potentially malicious external URL detected (medium risk: 0.30). The installation command references harshsinghmp/muse-skills, an unofficial personal GitHub repository, which constitutes an unverifiable runtime or setup dependency.