skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pricing-diagnostics/Gen Agent Trust Hub
revenue-cloud-pricing-diagnostics
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external Salesforce metadata and org data, creating a potential vector for instructions embedded within the data being processed.
- Ingestion points: The agent reads Salesforce metadata XML files (including
.field-meta.xml,.contextDefinition-meta.xml, and.expressionSetVersion-meta.xml) and retrieves live data via SOQL queries. - Boundary markers: The workflow lacks explicit delimiters or instructions to ignore potential natural language commands embedded within the technical metadata fields (e.g., in field descriptions or formulas).
- Capability inventory: The skill instructs the agent to perform data-retrieval operations using SOQL and the Salesforce Business Rules Engine Connect API.
- Sanitization: No validation or sanitization mechanisms are specified for the content retrieved from metadata or query results.
- [COMMAND_EXECUTION]: The skill contains specific instructions and templates for executing SOQL queries and Salesforce REST API requests (Connect API) to gather pricing implementation details from the environment.
Audit Metadata