dynamics-365-crm

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the processing of untrusted data from Dynamics 365 entities, which represents a surface for indirect prompt injection attacks where malicious instructions hidden in data could influence the agent's behavior.
  • Ingestion points: Data is ingested through API calls to entities like leads, incidents (cases), emails, and knowledgearticles, as described in SKILL.md and references/d365-customer-service-reference.md.
  • Boundary markers: The documentation does not include explicit instructions to use delimiters or "ignore embedded instructions" warnings when processing content from these external CRM sources.
  • Capability inventory: The skill allows the use of powerful tools including Bash, Write, and Edit, which could be targeted by an attacker if an injection is successful.
  • Sanitization: The provided code samples and instructions lack patterns for sanitizing, escaping, or validating the content retrieved from the CRM before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:10 AM
Security Audit — agent-trust-hub — dynamics-365-crm