charm-person

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely as a set of instructional prompts for text generation. It does not include any scripts, binary files, or configuration that would trigger command execution or file system access.
  • [SAFE]: No external dependencies or remote code patterns were detected. The skill specifically states it has no runtime dependencies beyond the standard agent environment.
  • [SAFE]: The instructions include ethical guardrails that explicitly forbid manipulation, lying about deadlines, or manufacturing false intimacy, reducing the risk of the agent being used for deceptive purposes.
  • [SAFE]: There are no indicators of obfuscation, credential exposure, or persistence mechanisms. The language used is thematic (e.g., 'spell', 'grimoire') but clearly maps to standard text-drafting tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:14 AM
Security Audit — agent-trust-hub — charm-person