The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists exclusively of Markdown documentation files (SKILL.md, references/review-patterns.md, and references/risk-assessment.md). There are no scripts (.js, .py, .sh), binaries, or configuration files that would execute code or perform system operations.
[CREDENTIALS_UNSAFE] (INFO): The file references/review-patterns.md contains a placeholder credential sk_live_abc123. This is explicitly labeled as a "Security Anti-Pattern" for educational purposes to demonstrate how not to handle secrets and does not pose a security risk.
[COMMAND_EXECUTION] (INFO): Documentation in references/review-patterns.md contains code snippets demonstrating command injection vulnerabilities. These are provided as negative examples for code review training and are not intended for execution by the agent.

code-review