charlierose-perspective

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for role-playing and communication guidance. All instructions are transparent and aligned with the described purpose.
  • [PROMPT_INJECTION]: Instructions define a specific persona and conversational style. There are no attempts to bypass safety guardrails or ignore system instructions.
  • [EXTERNAL_DOWNLOADS]: The documentation mentions an installation command using npx, which is a standard distribution method for this skill's ecosystem. No suspicious remote code execution or unauthorized downloads were found.
  • [DATA_EXFILTRATION]: No network requests, hardcoded credentials, or sensitive file path accesses were detected within the skill body or reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 03:34 AM
Security Audit — agent-trust-hub — charlierose-perspective