whop-dev

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

• Third-party content exposure detected (medium risk: 0.30). The workflow handles payment and membership webhook events ingested via HTTP POST requests (rules/payments-webhooks.md), exposing the agent to outsider-submitted payloads.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains an auto-install command referencing GitHub repositories (https://github.com/anthropics/skills, https://github.com/vercel-labs/agent-skills, and https://supabase/agent-skills) which execute at setup time to install companion skills via npx skills add, falling under the common/reputable unofficial tier for shared skill packages.

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

• Direct money access detected (high risk: 0.70). The skill provides guidance for building Next.js apps with the Whop platform, including creating checkout flows, payment webhooks, payouts, and billing portals via the @whop/sdk. Because these constitute direct financial operations (transfers, charges, checkouts) without documented independent access control enforced by the execution layer for these flows, it falls under the high severity tier.