plugins

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes patterns for processing data from Dataverse entities within plugins. This creates a surface for indirect prompt injection where malicious data stored in Dataverse could influence the logic of the plugin or downstream systems. \n
  • Ingestion points: Data entering the execution context through context.InputParameters["Target"] or context.PreEntityImages (documented in samples/SetDefaultsOnCreate.cs and common-patterns.md). \n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded directives are used when processing Dataverse entity attributes. \n
  • Capability inventory: Plugins have the capability to perform CRUD operations via IOrganizationService and make external network calls using HttpClient (documented in common-patterns.md and sandbox-performance.md). \n
  • Sanitization: The provided code snippets do not demonstrate sanitization or validation of external data before it is used in logic or further operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 02:03 AM
Security Audit — agent-trust-hub — plugins