The Agent Skills Directory

[SAFE]: The skill provides a comprehensive framework for systematic code analysis across multiple programming languages and formats.
[SAFE]: No malicious patterns such as obfuscation, credential harvesting, or unauthorized network activity were identified.
[SAFE]: The skill actively promotes security best practices by instructing the agent to evaluate code for common vulnerabilities.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing untrusted external code.
Ingestion points: Code snippets and files provided for review.
Boundary markers: None explicitly defined.
Capability inventory: General tool access is available via allowed-tools set to all.
Sanitization: Input code is analyzed but not executed or sanitized. This surface is inherent to the skill's primary purpose and is assessed as safe within this context.

code-reviewer