cleanup-audit

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [General Security] (SAFE): No executable code, shell commands, or obfuscated content were found. The skill is purely instructional and lacks any dangerous capabilities.
  • [Indirect Prompt Injection] (INFO): The skill is designed to analyze external source code for complexity hotspots. Evidence: 1. Ingestion points: Untrusted source code files. 2. Boundary markers: Absent. 3. Capability inventory: No file-write, network, or execution capabilities detected in SKILL.md. 4. Sanitization: Absent. Because the skill only outputs textual analysis, the threat is negligible.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 08:07 AM