gnnwr-spatial-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing several external dependencies to function correctly.
  • Python Dependencies: Instructs the user to run pip install gnnwr for the core library, and optionally geopandas, contextily, folium, and matplotlib for visualization tasks.
  • Node.js Tooling: The README recommends using npx skills add SteadfastAsArt/gnnwr-agent-skill for installation. This command downloads and executes the skills package from the npm registry.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external data files.
  • Ingestion points: The skill instructions involve reading user-provided data via pd.read_csv("data.csv") in SKILL.md and AGENTS.md.
  • Boundary markers: No specific boundary markers or "ignore instructions" warnings are provided to the agent for the data ingestion step.
  • Capability inventory: The skill utilizes the gnnwr library for regression modeling and various visualization tools (matplotlib, folium, geopandas) to generate maps and reports. No high-risk capabilities such as arbitrary subprocess execution or network-based exfiltration were identified in the provided scripts.
  • Sanitization: The instructions do not include data validation or sanitization steps before the data is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:00 AM
Security Audit — agent-trust-hub — gnnwr-spatial-analysis