creating-an-endpoint
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill functions as a set of instructions for managing platform-specific resources.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves the creation of endpoints that execute user-defined HogQL queries, it identifies the potential for injection attacks. It provides explicit remediation guidance, instructing the agent to prevent users from creating variables that allow arbitrary SQL injection (e.g., a
where_clausevariable). This demonstrates a proactive security posture regarding the data ingestion surface.
Audit Metadata