code-polish

Warn

Audited by Runlayer on Feb 23, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
78%
Files
1
Flagged
1
Chunks
1
Flagged Files (1)
SKILL.mdHIGH
78.3%

Malicious tool definition detected

Tool: SKILL.md Description: --- argument-hint: '' context: fork disable-model-invocation: false name: code-polish user-invocable: true description: This skill should be used when the user asks to "polish code", "simplify and review", "clean up and review code", "full code polish", "simplify then review", "refactor and review", "simplify and fix", "clean up and fix", or wants a combined simplification and review workflow on recently changed code.

Audit Metadata
Max File Score
78%
Classification
UNKNOWN_SERVER
Files Scanned
1
Files Flagged
1
Chunks Analyzed
1
Analyzed
Feb 23, 2026, 04:01 PM
Security Audit — runlayer — code-polish