service-itsm-agentic-setup-itsm-agentforce-permset-assign

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Salesforce CLI (sf) to query and manage org configuration. It operates using the existing authenticated CLI session and explicitly prohibits raw access token extraction, adhering to security best practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Salesforce API responses (Ingestion points: sf CLI output captures in /tmp/). It employs local Node.js scripts as a validation layer to classify results deterministically (Boundary markers: script-based classification logic replaces prose interpretation). While the skill can modify org permissions (Capability inventory: sf org assign permset), all inputs are strictly validated (Sanitization: Regex validation for Salesforce IDs in resolve-target-user.mjs and hardcoded allow-lists for persona names).
  • [SAFE]: Administrative actions, including permission set and license assignments, are gated by a mandatory confirmation prompt (AskUserQuestion), ensuring no modifications occur without explicit user consent.
  • [SAFE]: All logic is contained within local scripts using standard libraries, with no remote code execution, external package downloads, or obfuscated code detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:41 AM
Security Audit — agent-trust-hub — service-itsm-agentic-setup-itsm-agentforce-permset-assign