create-chart
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for interacting with Amplitude's API to build and save charts. It does not contain any suspicious commands, hardcoded credentials, or persistence mechanisms. All referenced tools and resources are consistent with the stated purpose of analyzing Amplitude data.
- [INDIRECT_PROMPT_INJECTION]: The skill uses natural language input to drive tool actions, which is an inherent attack surface for indirect instructions.
- Ingestion points: User-provided natural language descriptions of the desired chart components.
- Boundary markers: No specific delimiters or safety instructions are defined to separate user input from agent instructions.
- Capability inventory: Includes the ability to search events, get properties, query datasets, and save chart edits within Amplitude.
- Sanitization: The instructions do not specify input validation or sanitization, relying instead on API response verification.
Audit Metadata