alphai-twitter
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill retrieves untrusted content from Twitter (X) via multiple API endpoints and a WebSocket stream, creating a surface for indirect prompt injection where malicious tweets could manipulate the agent's behavior.
- Ingestion points: Untrusted tweet text is ingested from endpoints such as monitorList, myList, x/search, x/tweets, and the WebSocket stream.
- Boundary markers: No specific boundary markers or isolation instructions are provided to separate the untrusted data from the agent's core logic.
- Capability inventory: The skill performs authenticated HTTP requests and WebSocket connections to the vendor's API gateway.
- Sanitization: The skill does not perform any sanitization or validation of the retrieved tweet text before passing it to the agent.
Audit Metadata