hydrogen-analytics-tracking

Fail

Audited by Snyk on Nov 13, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate tracking guide, but it hard-codes "granted" consent on webhook-derived events and recommends sending PII and identifiers when the visitor has denied consent, which overrides the shopper's choice without any malicious intent.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow is building tracking code from first-party skill docs and provider docs, but the Shopify orders/create webhook path carries cart attributes that shoppers can set through crafted ?gclid=/?ref= URL params, and the guide has the agent read them back into order-derived events.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The decisive inbound dependency is the instructed setup command npx skills add Weaverse/shopify-hydrogen-skills, which installs executable helper scripts the skill runs, and its GitHub locator is attributable to the Weaverse organization, but ownership is inferred from the repository name rather than independently verified, so it is treated as common/reputable unofficial (medium) under recall-first.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 06:26 PM
Issues
3