clinical-reports

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes the OpenRouter API at https://openrouter.ai/api/v1 at runtime (via generate_schematic_ai.py / generate_schematic.py) to generate and review schematics, and the API responses (Gemini review critiques) are used to modify prompts and control iterative generation, so this external endpoint directly influences agent instructions and is a required runtime dependency.

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

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