Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed PowPow signup helper that creates accounts and optional payment orders, with session-token handling that users should treat carefully.
Install only if you want an agent to help create a PowPow account. Provide the password and email code only when you intend to register, treat generated one-click login links like active login sessions, prefer the packaged screenshots over remote fallbacks, and run cleanup when finished.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
Referenced artifact was not completely inspected
- 핵심 스크립트 `scripts/powpow-register.mjs`: **의존성 제로**, **Node ≥ 18** 필요. 시작 전에 `node scripts/powpow-register.mjs status`를 한 번 실행해 환경을 확인합니다.
The skill description is written as a Korean-first experience and presents the workflow and behavior without offering any language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific, which is not documented here.
The skill clearly instructs the agent to execute Node scripts, use environment variables for passwords, and send requests to an external service, yet it declares no explicit tool scope or permission boundaries. This creates an authorization and transparency gap: an agent/runtime may permit broader-than-expected env and network access, increasing the chance of over-collection, misuse of local secrets, or unintended outbound requests.
The description says the agent can generate checkout flows, track payments, and support Alipay/PayPal upgrades, but it does not provide a prominent upfront warning that the agent may create orders, open payment pages, and poll payment status. Users may not expect transaction-related actions to be initiated or monitored by the agent, which raises consent, financial, and trust risks even if the agent never directly handles payment credentials.
The description says the agent can generate checkout flows, track payments, and support Alipay/PayPal upgrades, but it does not provide a prominent upfront warning that the agent may create orders, open payment pages, and poll payment status. Users may not expect transaction-related actions to be initiated or monitored by the agent, which raises consent, financial, and trust risks even if the agent never directly handles payment credentials.
The manifest sets the skill language to "ko" and the visible display text is in Korean, but the file does not indicate that users can opt into another language or that the skill is intentionally limited to a Korean-only regional context. This creates a natural-language policy concern because it appears to impose a specific language without user choice.
The instructions require maintaining a fixed tone and ending every turn with a specific '다음 단계' block, and the document overall is written as a Korean-only interaction pattern with no user language choice. This creates a language/locale policy concern because the skill does not offer opt-in or alternatives for users who may prefer another language.
The entire skill file is presented in Korean, including operational instructions and user-facing guidance, with no indication that users may choose another language or that the skill is intentionally limited to Korean-speaking contexts. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.
This markdown file contains a forced locale pattern by presenting the operative account message in Chinese text, with Korean only as a parenthetical explanation. Under the policy, language constraints should not be imposed unless the skill offers a language choice or clearly documents a justified locale restriction.
The troubleshooting table repeatedly instructs around Chinese-only platform strings such as account, registration, and login errors, but the file does not say the skill is restricted to a Chinese-language locale or that users can choose another language. That creates a natural-language locale policy concern for a general skill reference.
The file instructs the agent to fall back to externally hosted screenshot URLs when local assets are missing, which can cause unannounced third-party network requests and leak user metadata such as IP address, user agent, timing, and possibly conversation context tied to the request. In a registration/login support skill, this is more sensitive because users may already be discussing account, email, activation, or payment issues, so silent remote fetches increase privacy and supply-chain risk.
The natural-language instructions and example user utterances are entirely in Korean, indicating the skill is designed to communicate in a specific language. Under SQP-3, forcing a specific language without user opt-in is a policy concern unless the locale constraint is explicitly documented and justified, which is not stated here.