kb-visualize
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external knowledge bundle (e.g., markdown files) to generate its graph model. This data is untrusted and could contain malicious instructions designed to influence the agent or the visualization output.
- Ingestion points: Knowledge bundle files located in the directory specified by
<bundle-dir>(defaultknowledge/). - Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent to disregard instructions embedded within the bundle files.
- Capability inventory: The skill executes a local Node.js script, writes files (HTML artifacts), and renders interactive UI components.
- Sanitization: No explicit sanitization or validation of the input markdown content is mentioned in the instructions; the skill relies on the logic within the
graph.mjsscript. - [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command running a Node.js script (
graph.mjs) located within the skill's own directory. This script processes user-supplied directories as arguments.
Audit Metadata