field-service-sobject-create-configure

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard Salesforce REST API endpoints (e.g., /services/data/v67.0/sobjects/) for schema discovery and record creation. All API interactions are performed through the platform's provided dispatch and dispatch_readonly tools, which operate within the agent's established security context.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads data from external sources (Salesforce schema and records) to influence subsequent actions (creating new records). While this represents a theoretical attack surface for indirect prompt injection, the instructions are limited to standard data model discovery and record construction, which are core to the skill's intended primary purpose.
  • [SAFE]: The skill is authored by a trusted vendor and manages data relationships through standard topological sorting and batch transactions without using dangerous execution patterns or obfuscation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:33 PM
Security Audit — agent-trust-hub — field-service-sobject-create-configure