salesforce-automation
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external service provider to function.
- Evidence: The setup instructions in
SKILL.mddirect users to addhttps://rube.app/mcpas an MCP server endpoint in their client configuration. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it ingests and processes untrusted data from Salesforce CRM records.
- Ingestion points: Salesforce data fields for Leads, Contacts, Accounts, Opportunities, and Tasks, as well as raw SOQL query results defined in the "Core Workflows" section of
SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters or provide the agent with guidance to ignore potential instructions embedded within the CRM data.
- Capability inventory: The skill allows for significant state changes and data access via tools such as
SALESFORCE_CREATE_LEAD,SALESFORCE_UPDATE_TASK, andSALESFORCE_RUN_SOQL_QUERY. - Sanitization: Absent. There is no evidence of input validation, escaping, or filtering of content retrieved from the Salesforce API before it is processed by the agent.
Audit Metadata