Skills
skills/aradotso/marketing-skills/salesforce-marketing-cloud-mcp/Gen Agent Trust Hub

salesforce-marketing-cloud-mcp

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions involve fetching source code and container images from external repositories.
  • Evidence: git clone https://github.com/vinkius-labs/salesforce-marketing-mcp.git in SKILL.md
  • Evidence: docker pull vinkius/salesforce-marketing-mcp in SKILL.md
  • [COMMAND_EXECUTION]: The skill instructs the user to execute shell commands for deployment and local environment preparation.
  • Evidence: npx mcpfusion deploy in SKILL.md
  • Evidence: npm install, npm run dev, and docker run commands in SKILL.md
  • [PROMPT_INJECTION]: The skill ingests data from external Data Extensions, creating a surface for indirect prompt injection if that data contains untrusted instructions.
  • Ingestion points: Data retrieved via the query_data_extension tool (SKILL.md)
  • Boundary markers: None present in the documented instructions.
  • Capability inventory: API triggers and data modification via trigger_journey and manage_subscriber tools (SKILL.md)
  • Sanitization: No sanitization or validation steps are described for the data extension contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:24 PM
Security Audit — agent-trust-hub — salesforce-marketing-cloud-mcp