NYC

finance-manager

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and parses arbitrary user-provided files (PDF/CSV/JSON) as part of its runtime workflow (see scripts/extract_pdf_data.py and scripts/analyze_finances.py), so untrusted third-party or user-generated content could be fed into the agent and enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:12 PM