skill-creator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions and templates for creating other skills. No malicious patterns were detected.- [COMMAND_EXECUTION]: The skill requests file system access tools (os.fs.read, os.fs.write, os.fs.list) which are necessary and appropriate for its function of managing skill files on disk.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill defines default storage paths (e.g., ~/.atomic-agent/skills/) which are standard for the atomic-agent environment and does not attempt to access sensitive user directories or credentials.- [PROMPT_INJECTION]: No attempts to override system instructions or safety filters were found. The instructional language is benign and helpful.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 05:38 PM
Security Audit — agent-trust-hub — skill-creator