python-craftsman
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The instructions in SKILL.md define a professional persona and operational principles without attempting to override safety constraints or access internal system prompts.- [DATA_EXFILTRATION] (SAFE): There are no patterns indicating sensitive data access or exfiltration. Mentions of network libraries (e.g., httpx, requests) are provided solely as examples for the user's benefit and are not utilized by the skill itself.- [COMMAND_EXECUTION] (SAFE): While the documentation mentions development tools like 'uv', 'poetry', and 'ruff', these are discussed in an advisory context. The skill does not contain logic to execute these commands on the host system.- [REMOTE_CODE_EXECUTION] (SAFE): No remote code patterns or external script downloads were identified. The skill is entirely self-contained within its markdown and reference files.- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded secrets, API keys, or private credential paths are present in the provided files.
Audit Metadata