create-dashboard

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Amplitude, including event names, entity definitions, and query results, which could theoretically contain instructions intended for the agent.
  • Ingestion points: Data enters the context through Amplitude:search_amp_data_taxonomy, Amplitude:search_amp_entities, Amplitude:get_amplitude_charts, and Amplitude:query_amplitude_data.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: The agent can create dashboards using Amplitude:use_amp_dashboards.
  • Sanitization: Not specified in the instructions; the skill relies on standard tool interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:11 PM