epistemic-extraction

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns or dangerous operations detected. The skill consists entirely of natural language instructions and a JSON schema.
  • [Indirect Prompt Injection] (LOW): The skill ingests external text which is a theoretical attack surface, but it lacks any capabilities (network, command, or file system) to execute malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:48 PM