Dynamics 365 Automation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external CRM records (leads, accounts, contacts), which could contain malicious instructions designed to influence the agent's subsequent actions.
- Ingestion points: Untrusted data enters the agent context through tools like
DYNAMICS365_DYNAMICSCRM_GET_A_LEADandDYNAMICS365_DYNAMICSCRM_GET_ALL_LEADSinSKILL.md. - Boundary markers: The skill does not define clear delimiters or specific instructions for the agent to ignore or isolate content found within the CRM fields.
- Capability inventory: The skill has the capability to create and modify numerous CRM entities including leads, opportunities, sales orders, and support cases, providing an attacker with a path to manipulate CRM state if the agent obeys injected instructions.
- Sanitization: The instructions do not specify any validation, filtering, or escaping of the external data before it is processed by the agent.
Audit Metadata