skills/clawlink-hq/skills/salesforce/Gen Agent Trust Hub

salesforce

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the @useclawlink/cli tool to perform operations such as login, connect, and run for Salesforce actions. These commands are executed via the shell to interact with the Salesforce API.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @useclawlink/cli package directly from the NPM registry at runtime.
  • [CREDENTIALS_UNSAFE]: The skill documentation specifies that authentication credentials for ClawLink are stored locally in a JSON file at ~/.clawlink/credentials.json. This is a standard practice for CLI-based authentication and is managed by the vendor's tool.
  • [DATA_EXPOSURE]: The skill accesses Salesforce data (records, fields, queries) which is the intended functionality of the integration. It supports both read and write operations within the user's CRM environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — salesforce