salesforce-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [External Dependency] (LOW): The skill requires the user to configure the Rube MCP server at https://rube.app/mcp. This is an external service and toolkit (Composio) not included in the predefined trusted list.
  • [Indirect Prompt Injection] (LOW): The skill processes data from Salesforce that may be controlled by external actors (Category 8).
  • Ingestion points: Multiple tool calls including SALESFORCE_SEARCH_LEADS, SALESFORCE_SEARCH_CONTACTS, SALESFORCE_SEARCH_ACCOUNTS, SALESFORCE_SEARCH_OPPORTUNITIES, and SALESFORCE_RUN_SOQL_QUERY (via SKILL.md).
  • Boundary markers: Absent; the skill does not instruct the agent to ignore instructions embedded within the CRM data.
  • Capability inventory: Extensive write capabilities including creating/updating records (SALESFORCE_CREATE_LEAD), managing tasks, and transferring ownership (SALESFORCE_MASS_TRANSFER_OWNERSHIP).
  • Sanitization: Absent; no mention of escaping or validating data retrieved from Salesforce before processing or displaying it.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:19 AM