dynamics-365-crm
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes workflows that ingest untrusted data from external sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Data is retrieved from various Dataverse entities including
leads,incidents(cases),emails, andknowledgearticles(as detailed inSKILL.mdand the reference files). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings to separate data fields from system instructions during record processing.
- Capability inventory: The agent is granted access to high-capability tools including
Bash,Write, andEdit, as well as file system discovery tools (Glob,Grep,Read). - Sanitization: There are no explicit instructions or patterns provided for sanitizing, escaping, or validating external content before it is processed by the agent or included in reports.
Audit Metadata