scientific-schematics
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill ingests untrusted user input via the description prompt and forwards it to an LLM. Evidence: 1. Ingestion point: 'prompt' argument in scripts/generate_schematic.py; 2. Boundary markers: absent in the wrapper script; 3. Capability inventory: network API calls and file writing; 4. Sanitization: none visible in the provided wrapper.
- [COMMAND_EXECUTION] (SAFE): scripts/generate_schematic.py uses subprocess.run with an argument list to call an internal script. This is a safe implementation that prevents shell injection.
- [CREDENTIALS_UNSAFE] (SAFE): Sensitive API keys are managed via environment variables as per the instructions in README.md and scripts/generate_schematic.py. Documentation uses non-functional placeholders which do not represent a credential leak.
Audit Metadata