skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes Python scripts init_skill.py and package_skill.py which perform legitimate local file system operations such as directory creation, file writing, and zipping to facilitate skill development.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes a curl command targeting localhost:62610 for local skill registration. No external network requests or remote script executions from untrusted sources were detected.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or attempts to access sensitive system paths (e.g., SSH keys or environment files) were found in any of the scripts or references.
  • [PROMPT_INJECTION]: The content of SKILL.md provides structural guidance and does not contain patterns designed to override agent safety protocols or hijack the conversation flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:57 PM