commerce-and-trade-competitiveness-data-hub

Warn

Audited by Snyk on Jun 24, 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 skill instructs agents to fetch live schema/instructions at runtime from the AgentPMT MCP (e.g., https://api.agentpmt.com/mcp/) via get_schema/get_instructions calls, and those returned instructions are treated as authoritative and directly control agent prompts/behavior.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 24, 2026, 04:25 AM
Issues
1