aks-cost-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates legitimate Azure cloud management tasks using defined tools such as
query_aks_costsandexecute_query. It uses placeholders for sensitive identifiers like subscription IDs and references official Microsoft documentation for setup instructions. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from external API responses (Azure Resource Graph and AKS cost data).
- Ingestion points: Data enters the context via the output of the
execute_query(Step 1) andquery_aks_costs(Steps 2 and 3) tools. - Boundary markers: The skill uses a step-by-step instructional structure but does not implement specific technical delimiters (like XML tags or markdown blocks) to isolate external data from the agent's instructions.
- Capability inventory: The skill possesses the ability to generate, validate, and execute Kusto queries and query cost management APIs.
- Sanitization: There is no evidence of explicit sanitization for fields like cluster names or namespace labels, which are processed as strings during the analysis phase.
Audit Metadata