skill-creator

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes utility scripts (init_skill.py, package_skill.py) for managing the local file system. These scripts perform standard operations such as creating directories, writing template files, and generating zip archives. The packaging script includes security-conscious checks to explicitly skip symlinks and verify that files stay within the designated skill root, preventing accidental inclusion of sensitive host files.
  • [EXTERNAL_DOWNLOADS]: No network operations, remote script fetching, or external resource downloads were detected in the skill instructions or associated scripts.
  • [DATA_EXFILTRATION]: Analysis found no evidence of sensitive file access (such as SSH keys or environment secrets) or attempts to transmit data to external domains.
  • [PROMPT_INJECTION]: The content is purely instructional for designing modular AI capabilities. It does not contain bypass instructions, safety overrides, or system prompt extraction patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:10 PM
Security Audit — agent-trust-hub — skill-creator