skill-review

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious behavior, obfuscation, or unauthorized exfiltration patterns were identified in the skill instructions or metadata.
  • [Indirect Prompt Injection] (SAFE): The skill processes untrusted data by reading external skill files, creating a theoretical surface for indirect prompt injection. However, the risk is mitigated by a strict instruction requiring explicit user approval before any modifications are staged, committed, or pushed. * Ingestion points: Step 1 (Reading files via Read, Glob, Grep). * Boundary markers: None identified. * Capability inventory: File modification and git operations (implied in Step 7). * Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 02:20 PM