salesforce

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the sf (Salesforce CLI) binary to execute operations including data management, authentication, and system diagnostics.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the official @salesforce/cli package from the npm registry. Salesforce is a well-known and trusted service provider.
  • [DATA_EXFILTRATION]: The skill facilitates the retrieval, export, and display of sensitive Salesforce CRM data, such as access tokens, customer records, and system metadata. This is normal behavior for a CRM tool.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data retrieved from Salesforce orgs which could contain malicious instructions. 1. Ingestion points: Results from sf data query and sf data search. 2. Boundary markers: Absent. 3. Capability inventory: Subprocess execution of sf commands, file writing via --output-file, and authenticated network requests via sf api request. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 05:19 PM