visualisation
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied technical descriptions to generate interactive HTML visualizations. The lack of sanitization instructions for this untrusted data creates a surface for indirect prompt injection.\n
- Ingestion points: User-provided data describing architectures, flows, and summaries (SKILL.md).\n
- Boundary markers: Absent; the skill does not define delimiters for separating user content from the visualization template.\n
- Capability inventory: The skill involves writing files to the local filesystem and executing the
opencommand (SKILL.md).\n - Sanitization: Absent; there are no instructions for escaping or filtering user-provided information before it is rendered in the HTML/JS file.\n- [COMMAND_EXECUTION]: The skill uses the
datecommand for generating unique filenames and theopencommand to launch the resulting visualization in a browser.
Audit Metadata