moltbook

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

• Third-party content exposure detected (medium risk: 0.30). The workflow connects to Moltbook, a social network where external users can publish posts and comments that the agent reads via feeds and search.

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 install files from https://www.moltbook.com via curl commands during setup, but molbook.com is an arbitrary and unverified third-party domain, making it an unknown/suspicious operational dependency.