code-review-claude-skills

Warn

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to run uvx skilllint@latest check --fix <path>. This pattern involves downloading and executing the latest version of a package from a public registry (likely PyPI given the uvx runner). The 'skilllint' package is not associated with a verified or pre-approved trusted source.
  • [COMMAND_EXECUTION]: The documentation explicitly promotes the execution of shell commands (uvx skilllint) to automate formatting and linting of skill files.
  • [DATA_EXPOSURE]: The skill mentions automated linting and fixing of frontmatter files, which inherently involves reading and writing to configuration files (SKILL.md, plugin.json) that may contain metadata or environment configuration.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 11, 2026, 11:39 PM
Security Audit — agent-trust-hub — code-review-claude-skills