using-neon

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to fetch documentation at runtime using curl (e.g. https://neon.tech/llms.txt and https://neon.tech/docs/), which would be retrieved and injected into the agent's context to directly influence prompts/responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:10 PM