proworkflow

Warn

Audited by Snyk on Nov 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow runs Membrane actions against the ProWorkflow API (Clients, Messages, Tasks, and similar records) and returns whatever the agent requests, so any outsider-authored free text in those records is only read after the agent selects and fetches it, which fits the low category.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (medium risk: 0.30). No direct payment operation is documented. The skill describes ProWorkflow management of Clients, Staffs, Quotes, Templates, Messages and Groups, and it does not describe transfers, charges, refunds, purchases or trades. The overview lists Invoice, Recurring Invoice and Expense as ProWorkflow entities (lines 28, 38-39), and the skill gives open-ended access through membrane action list/action run ("Use action names and parameters as needed") and a raw proxy to the ProWorkflow API. Under recall-first, that plausibly lets the agent create real invoices or billable expense records, which is an indirect financial operation. The skill does not document a specific invoice-creation workflow, so this is a judgment call. Indirect operations do not require a control test, so the tier is medium.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 15, 2026, 12:33 AM
Issues
2