skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or persistence mechanisms were detected. The skill instructions and scripts are well-structured and follow established security best practices.
  • [COMMAND_EXECUTION]: The skill provides Python utilities (init_skill.py, package_skill.py, quick_validate.py) intended for local development workflows. These scripts perform deterministic file operations (creating, reading, and zipping files) based on explicit user-provided paths.
  • [DATA_EXFILTRATION]: The packaging logic in scripts/package_skill.py explicitly mitigates unauthorized data exposure by skipping symbolic links and verifying that all resolved file paths remain within the intended skill root directory (_is_within check). This prevents malicious skills from attempting to bundle sensitive system files via path traversal or link manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:31 PM
Security Audit — agent-trust-hub — skill-creator