content-auditor
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as credential theft, privilege escalation, or persistence mechanisms, were detected in the skill instructions.
- [COMMAND_EXECUTION]: The skill defines usage patterns for file and directory auditing (e.g.,
/content-auditor --file). These commands are descriptive of the skill's intended diagnostic purpose and represent standard agent interactions with localized content. - [PROMPT_INJECTION]: The skill contains internal guardrails and behavioral instructions (e.g., 'Audit, Don't Rewrite' and 'AI/human split is non-negotiable') that serve to define the agent's task-specific role and prevent hallucination, rather than attempting to bypass safety filters.
- [DATA_EXFILTRATION]: No network-based exfiltration or suspicious external communications were found. The skill operates purely on content provided by the user within the agent's environment.
Audit Metadata