salesforce-automation

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes an external MCP server endpoint (https://rube.app/mcp) to provide its core Salesforce automation capabilities. This is a standard integration method for MCP-based skills.
  • [PROMPT_INJECTION]: The skill processes external data retrieved from Salesforce (e.g., Lead and Contact fields), which creates a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in CRM records.
  • Ingestion points: Data is ingested from Salesforce through tools such as SALESFORCE_LIST_LEADS, SALESFORCE_SEARCH_CONTACTS, and SALESFORCE_QUERY as defined in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions within the retrieved CRM data.
  • Capability inventory: The skill provides significant capabilities including data creation, modification, and execution of arbitrary SOQL queries via the tools listed in SKILL.md.
  • Sanitization: There are no explicit sanitization steps mentioned for processing data returned from the Salesforce API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 07:57 AM