skills/featherhunter/skills/medal/Gen Agent Trust Hub

medal

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/generate_medal_gif.py utilizes subprocess.run to call ffmpeg for GIF assembly. The implementation is secure as it passes arguments as a list rather than a shell string, preventing command injection vulnerabilities.
  • [SAFE]: The scripts/medal.py utility includes a _normalize_file_path function that explicitly validates and restricts file operations to the directory defined by the MEDAL_RESOURCE_PATH environment variable, mitigating directory traversal risks.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or credentials were found in the source code or configuration files.
  • [DATA_EXFILTRATION]: There is no evidence of sensitive data being sent to external servers. All data processing and file access are confined to local directories specified by the user.
  • [PROMPT_INJECTION]: The skill instructions and role-play elements are focused on the intended functionality and do not attempt to bypass system safety filters or exfiltrate configuration data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:02 PM
Security Audit — agent-trust-hub — medal