ax-audit
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected. The skill's functionality is consistent with its stated purpose of auditing agentic applications.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes code from repositories being audited. An attacker could potentially embed instructions in the source code to manipulate audit results. This is an inherent risk for auditing tools and is addressed by the model's underlying safety filters.
- Ingestion points: Git diff and ripgrep output from the analyzed codebase.
- Boundary markers: None identified in the processing logic.
- Capability inventory: Uses shell commands (rg, git, awk, sed) to perform audits.
- Sanitization: No specific sanitization of ingested code content was found.
Audit Metadata