The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any malicious patterns or security vulnerabilities.
[NO_CODE]: This skill consists of markdown instructions and metadata only; no executable scripts or binary files are present.
[DATA_EXFILTRATION]: No sensitive file access or network communication patterns were identified in the skill instructions.
[REMOTE_CODE_EXECUTION]: The skill does not contain any instructions to download or execute code from external or untrusted sources.
[PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected in the instructions.

code-reviewer