skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill contains Python scripts (package_skill.py, quick_validate.py) designed to be executed via command line. These scripts perform routine file operations: reading directories, validating YAML frontmatter, and creating ZIP archives. All operations are local and triggered by the user.
  • [DATA_EXFILTRATION] (SAFE): No network operations or calls to external domains were found. The skill does not access sensitive system paths (e.g., ~/.ssh, ~/.aws).
  • [REMOTE_CODE_EXECUTION] (SAFE): There are no patterns for downloading or executing remote code. All logic is contained within the local Python files.
  • [PROMPT_INJECTION] (SAFE): The documentation files (output-patterns.md, workflows.md) contain instructional templates for AI agents. These templates follow standard patterns and do not contain attempts to bypass safety filters or override system constraints.
  • [DYNAMIC_EXECUTION] (SAFE): The scripts use yaml.safe_load() for parsing metadata, which is the recommended secure practice to prevent arbitrary code execution during deserialization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM