NYC

financial-document-parser

Warn

Audited by Snyk on Feb 16, 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 financial PDFs and images (see "Use when the user provides financial PDFs or images" and the activation examples in SKILL.md), which are untrusted third-party content the agent will read and could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:18 AM