Fanvue
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources which could be used for indirect prompt injection attacks. An attacker sending instructions via chat or comments could potentially influence the agent's behavior. \n
- Ingestion points: The skill reads external content through endpoints like
GET /chat-messagesandGET /posts/:uuid/comments(as documented inapi-reference.mdandSKILL.md). \n - Boundary markers: The skill instructions lack explicit delimiters or safety warnings to help the agent distinguish between data and instructions within the ingested content. \n
- Capability inventory: The skill provides extensive write permissions, including the ability to send direct messages (
POST /chat-messages), mass messages (POST /chat-messages/mass), and create public posts (POST /posts). \n - Sanitization: No evidence of input sanitization or validation is present in the skill's scripts or documentation.
Audit Metadata