crosspost
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it transforms potentially untrusted source content into platform-specific social media posts. \n
- Ingestion points: Untrusted source content provided by the user or generated by secondary skills like content-engine. \n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the adaptation logic. \n
- Capability inventory: The skill possesses the ability to perform network requests via the requests library and interface with external platforms through the x-api skill. \n
- Sanitization: There is no evidence of input validation, escaping, or filtering for instructions embedded within the source content.\n- [DATA_EXFILTRATION]: The skill provides an example Python implementation that performs network operations via requests.post to a remote service (your-crosspost-service.example). While intended as a placeholder, this demonstrates a pattern for transmitting content to external infrastructure.
Audit Metadata