unsafe-checker

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists exclusively of Markdown documentation and JSON configuration; no executable scripts (e.g., Python or JavaScript) are present.
  • [Prompt Injection] (SAFE): Analysis of the skill instructions and metadata revealed no attempts to override safety filters or manipulate the agent's behavior.
  • [Data Exposure & Exfiltration] (SAFE): No mechanisms for accessing sensitive system files or exfiltrating data via network requests were found.
  • [Indirect Prompt Injection] (SAFE): The skill is designed to read untrusted code, but lacks any write or network capabilities that could be exploited. 1. Ingestion points: Files matching **/*.rs via globbing. 2. Boundary markers: Absent. 3. Capability inventory: Read, Grep, and Glob tools for file analysis. 4. Sanitization: Absent as the skill provides review guidelines rather than data sanitization logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:46 PM