The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and guidelines for reviewing code comments. It does not contain any executable code, scripts, or remote dependencies.
[SAFE]: No network operations, sensitive file access, or privilege escalation commands were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill processes external source code which could contain malicious comments, the instructions focus strictly on comment classification (Remove, Reduce, Keep) and explicitly prohibit modifying implementation behavior. This narrow scope effectively mitigates the risk of instructions embedded in comments being executed by the agent.

comment-review