hermes-persona

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional prompts in Markdown format. It does not include any executable scripts, binary files, or automated commands.
  • [SAFE]: No network operations, data exfiltration patterns, or attempts to access sensitive system files were detected.
  • [SAFE]: The persona instructions are stylistic and formatting-focused. They do not contain patterns intended to bypass safety filters or extract system prompts.
  • [SAFE]: The recommended method for persisting personas across sessions involves adding configuration to the CLAUDE.md file, which is the standard mechanism for session-wide instructions in supported environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 05:23 PM
Security Audit — agent-trust-hub — hermes-persona