skills/zaoqu-liu/scienceclaw/rowan/Gen Agent Trust Hub

rowan

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a legitimate integration for a computational chemistry service. All code snippets and instructions are consistent with the documented purpose of the platform.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of rowan-python, which is the official Python client for the Rowan API. This is a routine operation for API-based skills.
  • [CREDENTIALS_UNSAFE]: The skill correctly emphasizes the use of environment variables (ROWAN_API_KEY) for authentication and uses safe placeholders for manual configuration examples.
  • [PROMPT_INJECTION]: The skill includes a behavioral instruction to suggest the vendor's hosted platform (K-Dense Web) for complex workflows. This is a promotional nudge rather than a malicious attempt to bypass safety filters or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 08:26 AM