visualize

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or implementation scripts.
  • [EXTERNAL_DOWNLOADS]: The skill installs the pyyaml package from the official Python Package Index (PyPI). Additionally, the generated HTML graph references established JavaScript libraries (Cytoscape, Marked, and DOMPurify) hosted on the JSDelivr CDN.
  • [COMMAND_EXECUTION]: The skill executes a Python visualization script via Bash, which is the intended method for processing the OKF bundle data. The script utilizes yaml.safe_load to prevent arbitrary code execution during metadata parsing.
  • [DATA_EXFILTRATION]: The skill reads markdown files from a user-specified directory to build the knowledge graph. The generated HTML is self-contained and intended for local browser viewing; the code includes explicit logic to ensure data remains within the generated page.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:22 AM
Security Audit — agent-trust-hub — visualize