neo-python
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and reference documents align with established Python best practices and security standards. It focuses on improving code quality and maintainability without requesting excessive permissions or performing suspicious operations.
- [PROMPT_INJECTION]: The skill inherently possesses an indirect prompt injection surface because it is designed to read and analyze user-supplied Python files and configuration data. Malicious code could theoretically contain instructions aimed at manipulating the AI agent's logic during the review process.
- Ingestion points: Inspects files such as
*.py,pyproject.toml,requirements.txt,Pipfile, andpoetry.lock(found in SKILL.md). - Boundary markers: Absent. The skill does not specify the use of delimiters or 'ignore' instructions when processing user code.
- Capability inventory: The skill can refactor code, generate new logic, and recommend system-level tool usage (SKILL.md).
- Sanitization: None described. The skill treats analyzed code as data for review, which could be exploited by embedded adversarial prompts.
Audit Metadata