connect-ai-dynamics365businesscentral
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for querying and processing data from external Dynamics 365 Business Central environments. Data residing in the ERP (such as customer records, invoice descriptions, or ledger entries) is considered untrusted external content that could contain embedded instructions intended to influence the agent's logic.
- Ingestion points: SQL queries performed against the
Dynamics365BusinessCentralconnector as documented throughoutSKILL.md(e.g., SELECT statements oncustomers,salesOrders, etc.). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data retrieved from the database.
- Capability inventory: The skill utilizes tool capabilities for data retrieval (
SELECT), record modification (INSERT,UPDATE), and specialized operations likeRequestRawValuefor fetching document streams. - Sanitization: While the skill provides guidance on correct SQL identifier quoting (e.g.,
[Contoso, Ltd.]) and specific AL enum encoding (e.g.,_x0020_for spaces), it does not include instructions for sanitizing the actual content of the retrieved business data.
Audit Metadata