AGENT LAB: SKILLS

pdf

Fail

Audited by Snyk on Feb 15, 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 includes examples that embed plaintext passwords in code and a CLI example passing a password as a command-line argument (qpdf --password=mypassword and writer.encrypt("userpassword", "ownerpassword")), which instructs handling secrets verbatim and is an insecure pattern that could lead to exfiltration.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:25 PM