The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown content and does not include any executable scripts, binaries, or configuration files.
[SAFE]: No network operations (e.g., curl, wget), remote code execution patterns, or external dependency downloads were detected.
[SAFE]: There is no evidence of hardcoded credentials, sensitive file path access, or data exfiltration mechanisms.
[SAFE]: The 'Security' section of the review guide explicitly instructs the agent to check for vulnerabilities such as SQL injection, XSS, and hardcoded secrets, promoting secure coding practices.
[PROMPT_INJECTION]: The skill contains no instructions attempting to override agent behavior, bypass safety filters, or extract system prompts.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external data (code changes), it does not provide any active capabilities (such as shell execution or network access) that could be exploited via malicious code comments or data strings. It functions purely as a set of analytical guidelines.

code-review-and-quality