dashboard-builder

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional text and does not provide executable scripts, binaries, or automated configuration files.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present in the recommended workflow.
  • Ingestion points: The agent is instructed to 'Inspect existing dashboards' in JSON format (Step 2 of the workflow).
  • Boundary markers: The instructions do not define delimiters or warnings to ignore embedded commands within the analyzed JSON files.
  • Capability inventory: The skill directs the agent to study, generate, and build dashboard JSON configurations.
  • Sanitization: There are no instructions provided for validating or sanitizing the contents of the inspected dashboard JSON before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — dashboard-builder