connect-ai-dynamics365businesscentral

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data from Dynamics 365 Business Central, which establishes an indirect prompt injection surface.
  • Ingestion points: The agent ingests data through SQL SELECT queries on tables like customers, salesOrders, and generalLedgerEntries in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within the retrieved data.
  • Capability inventory: The skill uses SQL capabilities (SELECT, INSERT, UPDATE) and stored procedures such as RequestRawValue via the CData Connect AI connector.
  • Sanitization: There are no explicit instructions for sanitizing or validating the data returned from the BC API before it is processed by the agent.
  • [SAFE]: The skill provides standard documentation and SQL patterns for a database connector. The use of vendor-specific tools and stored procedures aligns with the stated purpose of querying Business Central data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:09 PM
Security Audit — agent-trust-hub — connect-ai-dynamics365businesscentral