sequential-thinking

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill sends runtime requests to the OpenRouter API (https://openrouter.ai/api/v1/chat/completions), and the model-generated responses are required for operation and are injected back into subsequent prompts (decomposition, step solving, verification, synthesis), so this external URL directly controls the agent's behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:47 PM