lytics-schema
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlandjqto interact with Lytics API endpoints for schema discovery and management. It also accesses~/.lytics/accounts.tomlto retrieve stored API credentials for multi-account operations.- [INDIRECT_PROMPT_INJECTION]: The skill processes metadata and logic from the Lytics API, such as field descriptions and segment definitions, which could contain instructions to influence agent behavior. - Ingestion points: User-defined strings retrieved via
GET /v2/schema/{table}/fieldandGET /v2/segment?table={table}in the optimization and discovery workflows. - Boundary markers: No explicit delimiters are used to separate external metadata from instructions.
- Capability inventory: The skill allows creating, updating, and deleting schema fields and mappings.
- Sanitization: No explicit sanitization or validation of the ingested metadata is mentioned.
Audit Metadata