building-a-dashboard

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to retrieve and process data from existing dashboards, insights, and templates. This data is potentially untrusted and could contain malicious instructions designed to influence the agent's actions during the creation or update of other resources.
  • Ingestion points: Untrusted data enters the agent context through the outputs of dashboards-get-all, dashboard-get, insights-list, insight-get, and dashboard-templates-retrieve as described in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions embedded within the retrieved data.
  • Capability inventory: The skill possesses write capabilities including insight-create, dashboard-create, dashboard-update, and dashboard-reorder-tiles across its workflow.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the retrieved content before it is used to perform subsequent actions or construct new dashboard components.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:48 PM
Security Audit — agent-trust-hub — building-a-dashboard