crosspost
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process and reformat external content for distribution, which creates a surface for indirect prompt injection. 1. Ingestion points: The skill takes source content and user context to generate adapted posts. 2. Boundary markers: There are no explicit delimiters or instructions defined to isolate the untrusted input from the agent's core instructions. 3. Capability inventory: The skill utilizes external APIs (such as x-api) and provides templates for network requests to distribution services. 4. Sanitization: No input validation or filtering of the content is specified before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill contains a Python implementation template that uses the requests library to transmit data to an external, non-whitelisted placeholder domain (your-crosspost-service.example). While the credentials are handled securely via environment variables, this demonstrates a functional pattern for data to be sent out of the local environment to third-party endpoints.
Audit Metadata