agency-chief-of-staff
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill provides detailed behavioral guidelines for an AI agent acting as a 'Chief of Staff'. These instructions focus on communication style, priority filtering, and process ownership. No attempts to bypass safety filters, disregard system instructions, or engage in malicious role-play (e.g., DAN) were found.
- [DATA_EXFILTRATION]: The analysis found no network operations, hardcoded credentials, or access to sensitive file paths. The skill's focus on maintaining a 'Decision Log' and 'Document Dependency Map' is strictly internal to its role in managing information for the user.
- [REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of remote code. The skill does not utilize package managers or external script execution mechanisms.
- [COMMAND_EXECUTION]: No shell commands, privilege escalation (like sudo), or persistence mechanisms were detected. The skill operates within the agent's standard conversational and file-manipulation boundaries.
- [OBFUSCATION]: The content is clear and uses standard Markdown and YAML formatting. No hidden strings, Base64 encoding of commands, zero-width characters, or homoglyphs were identified.
Audit Metadata