crosspost
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill contains a Python code snippet that demonstrates how to send content to the
api.postbridge.iodomain. This network operation is consistent with the skill's primary function of content distribution. - [PROMPT_INJECTION]: The skill processes user-supplied text for social media posting, which introduces a surface for indirect prompt injection.
- Ingestion points: User-provided source content used in the cross-posting workflow.
- Boundary markers: No explicit boundary markers or isolation techniques are mentioned for handling untrusted content.
- Capability inventory: Network requests via social media APIs and the third-party Postbridge service.
- Sanitization: No validation or sanitization of the input content is implemented.
Audit Metadata