Skills
Navigate
skills/full-stack-skills/codeguard-skills/codeguard-python/Gen Agent Trust Hub

codeguard-python

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to run the ruff linter and formatter as specified in SKILL.md. Specific commands include ruff --version and ruff check ..
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code and configuration files from the project environment to perform its analysis.
  • Ingestion points: Python source code (.py) and project configuration files (pyproject.toml, setup.py) identified in SKILL.md.
  • Boundary markers: No delimiters or specific ignore-instructions are used when processing file content.
  • Capability inventory: The skill has capabilities for shell command execution and local file modification as defined in SKILL.md and references/tooling/toolchain.md.
  • Sanitization: No sanitization of the project file content is mentioned in the workflow.
  • [SAFE]: The skill's instructions in SKILL.md incorporate strong security principles, such as prohibiting network access for dependency installation and ensuring transparency by distinguishing between verified and unverified tool outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 04:47 AM