pp-doordash

Warn

Audited by Snyk on Aug 18, 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 runtime workflow exposes DoorDash “read-only” commands that accept outsider-supplied free-text search queries (e.g., searchcreate-autocomplete-facet-feed) and may ingest that query without selecting a specific pre-existing item first.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill instructs installing a required CLI by running "go install github.com/mvanhorn/printing-press-library/library/commerce/doordash/cmd/doordash-pp-cli@latest", which will fetch and execute remote code from that GitHub path at install/runtime, so this external dependency can directly execute code on the agent host.

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

  • Direct money access detected (high risk: 1.00). The skill exposes DoorDash GraphQL mutations that can submit live orders and modify carts (not just read-only). Specifically, it documents "create-create-order-from-cart — Mutation: submit a DoorDash order from a cart" plus add/remove/update-cart-item mutations and a payment-status poll. Those are explicit transaction-executing operations that can result in charges to a user's payment method (even if some commands are gated), so the skill grants direct financial execution capability.

Issues (3)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 18, 2026, 08:10 PM
Issues
3
Security Audit — snyk — pp-doordash