create-chart

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from the Amplitude environment.
  • Ingestion points: Untrusted data enters the agent context via tool outputs from Amplitude:search, Amplitude:get_event_properties, and Amplitude:get_charts (e.g., event descriptions or existing chart names).
  • Boundary markers: Absent. The instructions do not provide delimiters or warnings to ignore potentially malicious instructions embedded in the retrieved metadata.
  • Capability inventory: The skill possesses the ability to execute queries through Amplitude:query_dataset and perform write operations via Amplitude:save_chart_edits.
  • Sanitization: Absent. There is no requirement for the agent to validate or sanitize external content before incorporating it into chart definitions or logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — create-chart