worldmonitor-intelligence-dashboard

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions in the troubleshooting section to install Ollama by piping a script from its official domain (ollama.ai) to a shell. This is a standard installation method for a well-known service intended to support local AI synthesis.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes several established libraries and tools, including globe.gl and deck.gl for map visualizations, and tauri-cli for building native desktop applications. These represent standard dependencies for the dashboard's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from over 435 external news feeds and API sources. This creates a surface for indirect prompt injection where malicious content in a news feed could attempt to influence the AI synthesizer. However, in the provided implementation, the AI's output is limited to generating summaries and signals for display, with no associated high-risk capabilities like file system modifications or shell command execution based on the synthesized content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 08:36 PM
Security Audit — agent-trust-hub — worldmonitor-intelligence-dashboard