prompts

Warn

Audited by Snyk on Apr 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 1.00). The manifest-schema explicitly shows a remote OpenAPI spec URL (e.g. "https://api.weather.example.com/openapi.json") which the skill warns is fetched at runtime and converted into MCP tools that directly influence agent capabilities, so this external URL is a runtime dependency that can control agent behavior.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 08:25 PM
Issues
1