agent-skills-creator
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a documentation and template library for developers creating new skills. It contains no active malicious logic or obfuscated instructions.\n- [COMMAND_EXECUTION]: The documentation includes guidelines for using shell and Python scripts for automation and verification. It promotes safe practices such as the 'Plan-Validate-Execute' pattern and explicit error handling to prevent non-deterministic or destructive behavior.\n- [EXTERNAL_DOWNLOADS]: Mentions the platform capability to install packages from official registries (npm, PyPI) at runtime. The skill itself does not reference any specific untrusted or suspicious third-party dependencies.\n- [PROMPT_INJECTION]: The skill uses instructional text to guide model behavior toward relevant tasks using 'Use when...' trigger phrases. No attempts to bypass safety protocols or override system instructions were found.
Audit Metadata