written-feedback-generator

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • NO_CODE (SAFE): This skill is entirely composed of markdown instructions and contains no scripts or executable code.
  • Indirect Prompt Injection (LOW): The skill ingests user feedback text which could potentially contain malicious instructions. 1. Ingestion points: User feedback context and local competency files. 2. Boundary markers: None present. 3. Capability inventory: Text generation only. 4. Sanitization: Slugification is performed on the role name before file lookup.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 01:26 PM