fin-guru-create-doc
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill references local file paths for templates and output storage. No network operations, sensitive file access (like SSH keys), or hardcoded credentials were found.\n- [Indirect Prompt Injection] (LOW): A surface for indirect prompt injection exists because the skill ingests external analysis data to generate documents. However, this is inherent to its primary function. (1) Ingestion: analysis data; (2) Boundary markers: Absent; (3) Capabilities: File-write to defined output path; (4) Sanitization: None mentioned.
Audit Metadata