agentforce-wizard-ui-forecasting-analytics-components-configure

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Salesforce organization via the load-tuner-metadata operation, which retrieves Opportunity custom fields and picklist values. This content is used to inform the save-tuner-metadata configuration process. The instructions do not specify explicit boundary markers or sanitization for these metadata fields before they are processed by the agent.
  • [DYNAMIC_EXECUTION]: The save-tuner-metadata operation involves the internal re-serialization and deserialization of the predictionConfig object by the backend controller. The skill documentation instructs the agent to manually format certain fields as JSON-encoded strings (e.g., excludedFields) to ensure successful deserialization into the internal prediction-config object.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 09:04 AM