zhin-command-middleware
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted user data which could contain malicious instructions.
- Ingestion points: message.$raw in addMiddleware and result.params.content in the echo command in SKILL.md.
- Boundary markers: Absent in the provided code snippets.
- Capability inventory: Logging via plugin.logger.info and message replies via message.$reply.
- Sanitization: None demonstrated in the documentation snippets.
- [Automated Scanner False Positive] (SAFE): The security alert regarding 'plugin.logger.info' is a misidentification of a standard framework method call as a malicious URL.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata