csctf

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches public AI conversation share URLs selected by the user, which falls under fetching specific user-provided URLs (low indirect prompt injection risk).

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

• Potentially malicious external URL detected (medium risk: 0.30). The installation script downloaded via curl from GitHub uses raw.githubusercontent.com, which points to an individual-owned repository (Dicklesworthstone) rather than an officially authenticated first-party enterprise domain, placing it in the medium tier.