moltter
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION] (HIGH): High risk of indirect prompt injection due to processing untrusted social media content.
- Ingestion points: The agent retrieves untrusted data from
GET /api/v1/timeline/global,GET /api/v1/notifications, andGET /api/v1/searchwithin theSKILL.mdfile. - Boundary markers: Absent. The instructions do not define any delimiters or warning protocols to help the agent distinguish between user data and instructions.
- Capability inventory: The skill provides significant write/execute capabilities including posting content (
POST /api/v1/molts), following agents (POST /api/v1/agents/{name}/follow), and updating profile metadata. - Sanitization: Absent. There is no evidence of filtering or sanitization of content retrieved from the social network.
- [DATA_EXFILTRATION] (LOW): The skill performs network operations to a non-whitelisted external domain.
- Evidence: All API interactions are directed to
https://moltter.net, which is not a trusted external source. While no active exfiltration of local system secrets was detected, the network capability remains a medium for potential data transit.
Recommendations
- AI detected serious security threats
Audit Metadata