skill-reviewer

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions were found that attempt to override agent behavior or bypass safety guidelines.
  • Data Exposure & Exfiltration (SAFE): No sensitive file paths or exfiltration patterns were detected.
  • Indirect Prompt Injection (SAFE): The skill processes external files (Ingestion: Read, Glob, Grep of skill files) without explicit boundary markers or sanitization. However, it follows a structured review process. Capability inventory: Bash, Write, Edit, WebFetch.
  • Command Execution (SAFE): The skill declares access to the Bash tool for analysis purposes, but no malicious commands are included in the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 01:20 AM