The Agent Skills Directory

[SAFE]: The instructional content is restricted to code review guidelines and contains no malicious directives.
[NO_CODE]: The skill does not include any scripts or executable logic, posing no risk of direct code execution.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted code.
Ingestion points: Processes external code change sets (SKILL.md).
Boundary markers: No specific boundary markers or 'ignore' instructions are provided for processed code.
Capability inventory: The skill is limited to generating text-based review feedback and has no system or network capabilities.
Sanitization: No sanitization of input code is performed.

code-reviewer