new-old-user-define
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operations are legitimate and follow a structured process for managing analytics properties. It verifies system resources using platform-specific tools and requires user confirmation for logical configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection through platform metadata and SQL results. Ingestion points: Metadata and SQL results from
ae-cli(SKILL.md Steps 1 and 2). Boundary markers: The skill relies on validation against metadata instead of explicit delimiters. Capability inventory: Use ofae-clifor querying and creating properties/tags. Sanitization: The agent is instructed to verify all field identifiers against the platform's metadata registry before usage, reducing the risk of malicious input exploitation. - [DYNAMIC_EXECUTION]: The skill performs dynamic SQL construction using predefined templates. This process is constrained to a fixed set of analytics functions and identifiers validated via the system's metadata API, ensuring safe execution.
Audit Metadata