product-manager

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

• Third-party content exposure detected (high risk: 0.80). The skill's PRD and security workflows (SKILL.md and references/prd-template.md / references/security-checklist.md) explicitly require agents to validate and consult public npm package metadata (and other open community sources) on the public web before installing dependencies, which forces the agent to fetch and interpret untrusted, user-generated third‑party content that can materially change dependency and execution decisions.

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

• Direct money access detected (high risk: 1.00). The skill explicitly references payment gateways and Stripe integration (e.g., the keyword "Stripe 集成", subscription/付费模型, and an example showing stripe usage and secret key handling). Those are specific, named payment-related APIs/operations rather than generic tooling. Even though the skill is primarily a product-manager guide, it contains concrete, payment-gateway–specific guidance (Stripe) which meets the criterion for Direct Financial Execution exposure.