lookup-values
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to retrieve and process categorical values from an external database to refine search filters. This creates a surface where untrusted data from the database could influence agent behavior.
- Ingestion points: Data retrieved via the
lookup_valuestool and results fromexecute_aqlqueries (referenced in SKILL.md). - Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potential commands or formatting within the retrieved database strings.
- Capability inventory: The agent can perform data lookups and execute subsequent AQL queries (
execute_aql) based on the findings. - Sanitization: The skill does not provide methods for sanitizing or escaping the retrieved text values before they are interpolated into the next steps of the conversation or query construction.
Audit Metadata