Skills
Navigate
skills/somnio-software/somnio-ai-tools/python-best-practices/Gen Agent Trust Hub

python-best-practices

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches Python best-practice guidelines and markdown standards from the author's official GitHub repository (somnio-software/somnio-ai-tools).
  • [PROMPT_INJECTION]: The skill analyzes untrusted source code provided by users, which serves as a surface for indirect prompt injection. 1. Ingestion points: Files are read using Read, Grep, Glob, and Bash tools across Wave 1 and Wave 2 analysis agents. 2. Boundary markers: The SKILL.md instructs agents to be professional, evidence-based, and to report "Unknown" if evidence is missing, though explicit sanitization for user-provided code is not detailed. 3. Capability inventory: The skill uses Bash, Write, Edit, and Agent tools, which could be leveraged if the agent follows instructions embedded in analyzed source code. 4. Sanitization: No specific content sanitization or boundary delimiters for untrusted code are implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 01:07 AM
Security Audit — agent-trust-hub — python-best-practices