NYC

honest-agent

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill programmatically injects instructions into the configuration files of other AI agents to alter their behavioral persona.
  • [COMMAND_EXECUTION] (LOW): The skill requires the agent to perform file system discovery and write operations across both project-specific and global user directories (e.g., home folder configurations for Claude Code, Aider, and Continue.dev).
  • [SAFE]: No obfuscation, remote code execution, or data exfiltration to external domains was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:05 PM