investigating-agentforce-architecture

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the sf CLI to query Salesforce metadata. Command execution is performed via subprocess.run using structured YAML recipes. All user-supplied inputs (org alias, agent API name, version) are regex-validated by a dedicated safety guard (scripts/_shared/fs_guard.py) to prevent shell injection.
  • [CREDENTIALS_UNSAFE]: The skill implements robust credential handling. A central REST client (scripts/rest_client.py) automatically redacts Salesforce access tokens from error messages and logs. It also includes a custom redirect handler that strips Authorization headers when crossing host boundaries.
  • [SAFE]: Analysis found no evidence of prompt injection, data exfiltration to unauthorized domains, or persistence mechanisms. The skill operates within restricted local data and cache directories (~/.vibe/data and ~/.vibe/cache).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:49 PM
Security Audit — agent-trust-hub — investigating-agentforce-architecture