clinical-decision-support

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

• Potentially malicious external URL detected (high risk: 0.90). The included schematic-generation scripts call the OpenRouter API (https://openrouter.ai/api/v1 and related https://openrouter.ai/keys) at runtime to generate images and to receive AI review/critique that the skill uses to iteratively refine prompts, so external content directly controls the agent's prompting/behavior.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)