add-dataverse

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill instructs the agent to use local command-line tools such as the Azure CLI (az), Power Apps CLI (pa), and npm. These tools are used for authentication, data source management, and building the application within the local environment.
  • Indirect Prompt Injection: The skill processes external data from Dataverse API responses (such as entity definitions) and user-provided schema designs. This ingestion surface represents a potential vector for indirect prompt injection if the source data contains unexpected instructions. The skill's instructions do not currently define explicit boundary markers or sanitization steps for this content.
  • Ingestion points: Dataverse entity definitions retrieved via network requests and user-provided design requirements.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined in the instructions.
  • Capability inventory: The skill possesses capabilities for command execution (via Bash and CLI tools), file system modification (Edit, Write), and network access.
  • Sanitization: No explicit sanitization or validation of external metadata is described in the reference materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:15 AM
Security Audit — agent-trust-hub — add-dataverse