clinical-reports

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime calls to the OpenRouter API (https://openrouter.ai/api/v1) from scripts/generate_schematic_ai.py (and wrappers) to generate images and obtain AI critique that is used to iteratively modify prompts and control generation, so external responses directly influence agent behavior.

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

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