service-catalog-template-deploy

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Salesforce CLI (sf) commands and local node scripts. The activate-verify.mjs script follows security best practices by using execFileSync with an argument array (shell:false) to prevent shell injection from user-supplied names.
  • [PRIVILEGE_ESCALATION]: The skill includes a self-healing mechanism that assigns necessary permission sets (UnifiedCatalogAdmin) and licenses to the current user if a 403 Forbidden error is encountered during the preflight check. This is a targeted administrative action required to enable the Unified Catalog feature for the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests template data from the Salesforce catalog. It mitigates potential injection risks by using a deterministic resolution script (resolve-template.mjs) that requires an exact single name match and stops on ambiguity, and by escaping user-supplied values in SOQL queries within the activation script.
  • [SAFE]: The skill demonstrates a strong security posture by using a "deterministic gate" approach for write operations, ensuring no code or commands are constructed via string interpolation of untrusted data, and verifying every deployment with a post-action re-read.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 04:35 PM
Security Audit — agent-trust-hub — service-catalog-template-deploy