The Agent Skills Directory

[SAFE]: The skill is a non-executable instructional document that defines a code review practice. No malicious scripts or command execution patterns were found.
[DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential exfiltration attempts were detected. The skill emphasizes security and privacy principles such as data minimization and encryption in its documentation.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads, package installations, or dynamic script execution. It correctly identifies the need to pin and scan dependencies as a best practice in the documentation.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety filters or override system prompts. The content is professionally scoped to healthcare governance and implementation correctness.
[OBFUSCATION]: The file content is entirely plain-text Markdown with no encoded strings (Base64, hex), zero-width characters, or hidden acrostics.

code-reviewer