run-aql
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes rows from external Holistics datasets which may contain untrusted content that could influence the agent's behavior.
- Ingestion points: The
execute_aqltool retrieves result rows from a Holistics dataset (referenced inSKILL.md). - Boundary markers: Absent. The instructions do not specify the use of delimiters or clear boundaries when the agent processes the retrieved data rows.
- Capability inventory: The skill uses the
execute_aqltool to perform data retrieval and displays results (including compiled SQL) to the agent. - Sanitization: Absent. While the instructions suggest using
validate-aqlfor query syntax and type-checking, there is no mechanism described for sanitizing the actual data content returned from the dataset before it enters the agent's context.
Audit Metadata