enhance-prompt

Warn

Audited by Snyk on Feb 27, 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 at runtime to "consult the official Stitch documentation" at https://stitch.withgoogle.com/docs/learn/prompting/, which means externally-hosted content could be fetched and directly influence or override the prompts/instructions the skill emits.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:50 PM