salesforce-automation

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration directs the agent to connect to an external Model Context Protocol (MCP) server at https://rube.app/mcp. This server provides the necessary tools for interfacing with Salesforce, representing the primary intended function of the skill.
  • [SAFE]: No hardcoded credentials, malicious scripts, or obfuscation techniques were detected in the skill instructions or metadata.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes content from an external CRM system.
  • Ingestion points: Salesforce records (Leads, Contacts, Accounts, Opportunities, Tasks) retrieved via search and list tools in SKILL.md.
  • Boundary markers: Absent. No instructions are provided to treat incoming data as untrusted or separate from system instructions.
  • Capability inventory: Substantial capabilities including creating, updating, and deleting Salesforce records and executing custom SOQL queries.
  • Sanitization: None described. The skill relies on the underlying model's safety protocols to handle malicious data embedded in Salesforce records.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:19 AM
Security Audit — agent-trust-hub — salesforce-automation