marketing-retention
Warn
Audited by Snyk on Aug 3, 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’s “Research Mode: Live Competitive & Benchmark Intelligence” uses
agent-browserto open third-party live URLs (e.g., competitors, churnkey blogs, Baremetrics, Stripe docs) and then runsagent-browser get text body, which ingests outsider-authored free text from those pages at runtime.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill's shared patterns instruct installation via "npx skills add https://github.com/vercel-labs/agent-browser", which fetches and installs remote code (a required runtime dependency for the agent-browser research mode) and therefore can execute remote code during setup.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly references payment gateway products and payment-recovery features (Stripe, Stripe Billing Smart Retries, Stripe Portal, Chargebee, Recurly, Braintree) and gives actionable directives to enable/integrate payment-recovery features (Card Updater / Account Updater, Smart Retries) and to "update billing/plan". These are specific payment-processing integrations rather than generic tooling, so the skill includes direct financial execution-related capabilities.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata