skills/jigx-com/skills/jigx-acumatica/Gen Agent Trust Hub

jigx-acumatica

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines patterns for processing data from external Acumatica ERP endpoints, which establishes a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through REST and OData responses as specified in references/acumatica-rest.md and references/acumatica-lookups-expands.md.
  • Boundary markers: There are no explicit instructions to use delimiters or 'ignore embedded instructions' warnings when processing external data.
  • Capability inventory: The skill utilizes DATA_PROVIDER_REST for data exchange and file uploads to the ERP system as described in references/acumatica-files-submit.md.
  • Sanitization: Instructions in references/acumatica-rest.md require filtering internal metadata from outbound payloads, but do not provide specific guidance for sanitizing or validating incoming data from the ERP.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 03:36 PM
Security Audit — agent-trust-hub — jigx-acumatica