azure-data-tables-java
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill correctly references official, well-maintained libraries from the Azure SDK ecosystem (
com.azure:azure-data-tables). - [SAFE]: Code examples consistently use secure placeholders (e.g.,
<your-connection-string>,<account-key>,<sas-token>) and explicitly advise the use of secret stores for sensitive configuration in production environments. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from Azure Table Storage, which represents a potential surface for indirect prompt injection if the stored data contains malicious instructions intended to manipulate the agent.
- Ingestion points: The skill demonstrates data retrieval through methods such as
tableClient.listEntities()andtableClient.getEntity()inSKILL.md. - Boundary markers: The provided code snippets do not include delimiters or specific instructions for the agent to treat retrieved entity properties as untrusted content.
- Capability inventory: The skill enables significant write and management capabilities, including
createEntity,updateEntity,deleteEntity, anddeleteTable, which could be targeted by an injection attack. - Sanitization: Examples do not show explicit validation or sanitization of entity data before it is processed or used in logic.
Audit Metadata