agency

Warn

Audited by Snyk on Oct 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The workflow monitors and reads client support emails and files dropped into .agency/support/inbox/, which can contain untrusted outsider-authored text.

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

  • Direct money access detected (medium risk: 0.30). The skill is an AI automation agency assistant that drafts cold emails, prepares sales calls, writes proposals, builds client automations, and drafts support replies. It does not execute direct financial transfers, charges, or purchases; its output includes pricing information and drafting proposals, which constitutes indirect financial exposure (creating bills, quotes, or proposals for downstream handling). Therefore, it falls under the indirect operation type, making the severity 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
Oct 26, 2026, 06:31 PM
Issues
2