dashboard-no-data-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate troubleshooting procedures for data analysis dashboards. It uses specialized CLI tools to perform its tasks and does not engage in suspicious behaviors.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from dashboard and report configurations, creating a potential surface for indirect prompt injection. However, this is a standard operational requirement for a diagnostic tool, and the risk is mitigated by the constrained output format and the nature of the tools used.
  • Ingestion points: Dashboard and report details are retrieved via analysis dashboard get and analysis report get in SKILL.md.
  • Boundary markers: Not explicitly defined.
  • Capability inventory: The skill uses analysis and metadata tools (analysis-meta, analysis dashboard, analysis adhoc) to query structured data; it lacks capabilities for file writing or unauthorized network communication.
  • Sanitization: No explicit sanitization or escaping of metadata is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 10:17 AM
Security Audit — agent-trust-hub — dashboard-no-data-troubleshooting