code-quality

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill triggers shell commands through the uv tool to run code analysis utilities.
  • [REMOTE_CODE_EXECUTION]: The instruction to run uv run pytest executes Python code located in the target directory. This represents a potential risk if the directory contains untrusted or malicious test scripts.
  • [PROMPT_INJECTION]: The skill processes external data (code files in a directory) and has the capability to execute commands based on that data.
  • Ingestion points: Reads .py files within a user-specified directory in SKILL.md.
  • Boundary markers: No delimiters or ignore instructions used.
  • Capability inventory: Executes shell commands via uv run in SKILL.md.
  • Sanitization: No input validation or code sanitization is performed before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 01:43 PM
Security Audit — agent-trust-hub — code-quality