NYC

invoice-organizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection from untrusted invoice data. 1. Ingestion points: Untrusted data enters the context through PDF/image invoice processing and metadata extraction (SKILL.md). 2. Boundary markers: None are present to distinguish between extracted data and instructions. 3. Capability inventory: The skill performs file system manipulation using fs.renameSync. 4. Sanitization: The provided code pattern demonstrates direct use of extracted variables (vendor, amount) in file paths without escaping or validation, which could facilitate path traversal if the invoice content is maliciously crafted.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM