connect-tool

Fail

Audited by Snyk on Nov 2, 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 prompt explicitly instructs the agent that if the user pastes an API key into the chat, to pipe it directly into a command using printf, which involves handling and passing raw secret values through the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.70). The skill downloads operational script and skill files from an arbitrary GitHub repository URL at runtime, representing a weak external dependency.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
HIGH
Analyzed
Nov 2, 2026, 08:07 AM
Issues
2