scientific-writing

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior or patterns detected across the 13 files. The skill adheres to its stated purpose of assisting with scientific manuscript preparation.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the OpenRouter API (openrouter.ai) to generate scientific images and schematics. This is a well-known service, and the interaction is limited to the skill's stated purpose. The use of the API is documented and consistent with legitimate functional requirements.
  • [COMMAND_EXECUTION]: The script scripts/generate_schematic.py uses subprocess.run to invoke an internal Python script (scripts/generate_schematic_ai.py). The command is constructed using a list of arguments, which prevents shell injection vulnerabilities, and it is limited to executing local skill components.
  • [CREDENTIALS_UNSAFE]: The skill requires an OPENROUTER_API_KEY for its image generation features. It correctly prompts the user to provide this key via environment variables or a .env file, which is a standard and secure practice for local development tools. No hardcoded credentials were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 08:08 PM
Security Audit — agent-trust-hub — scientific-writing