Chat with PDF

Fail

Audited by Snyk on Mar 9, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill's outputs explicitly include verbatim quotes and extraction tables from PDFs (and asks for passwords to open protected PDFs), so if a document contains API keys, tokens, or passwords the LLM would be expected to reproduce them in its responses, creating an exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 9, 2026, 08:20 AM