Security audit
Security checks for vulnerabilities and agentic risk
This skill automates PowPow account registration and optional checkout in a disclosed, official-domain-only way, with sensitive session state that users should clean up after use.
Install only if you want a Russian-language assistant to create a PowPow account through the official PowPow site. Treat the one-click login URL and temporary JWT state as account access credentials, run cleanup when finished, and only proceed with the optional checkout when you are ready to pay in Alipay or PayPal yourself.
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Referenced artifact was not completely inspected
- Основной скрипт `scripts/powpow-register.mjs`: **ноль зависимостей**, требует **Node ≥ 18**. Перед началом выполните один раз `node scripts/powpow-register.mj
Suspicious Unicode normalization or mixed-script content
The entire skill description is written only in Russian, and there is no indication that the skill supports other languages, offers language choice, or is restricted to a justified Russian-language deployment context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Suspicious Unicode normalization or mixed-script content
The Conversation UX section mandates a fixed communication style entirely in Russian, including a required fixed closing block and example phrasing. There is no indication that the user can choose another language or that the locale restriction is optional, which creates a language/locale policy concern.
The manifest explicitly sets the skill language to "ru", while other fields include mixed Chinese text and there is no natural-language indication that the user can choose a different language or that the skill is intentionally restricted to a Russian-speaking region. This can violate language/locale policy because it imposes a specific language without opt-in or documented justification.
Suspicious Unicode normalization or mixed-script content
These lines prescribe a fixed communication style and explicitly require continuing with the same tone and a specific response structure, in a Russian-language skill document, without any opt-in or alternative locale/language handling. Under the policy, forcing a specific language or locale without user choice is a natural-language policy violation.
Suspicious Unicode normalization or mixed-script content
Natural-language policy violations include forcing a specific language without user opt-in. The entire skill instruction file is written only in Russian, while also embedding some fixed English and Chinese UI text, and nowhere indicates that language is optional or limited to a justified region-specific use case.
The skill instructs the agent to write attacker-controlled or externally supplied payment HTML to a temporary local file and open it via a system command, but it does not clearly warn the user or constrain how this launch occurs. This creates a trust-boundary issue: browser-launch behavior and local file handling can be abused for unsafe local execution patterns, phishing-like UX, or opening untrusted active content under the agent's authority.
Suspicious Unicode normalization or mixed-script content
The file title and the entire instructional content are written in Russian, which imposes a specific language choice on operators reading or using the skill. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; no such opt-in or justification appears here.
All user-facing instructions in this file are in Russian, and there is no indication that the user may choose another language or that the skill is intentionally restricted to a Russian-speaking context. Under the policy, forcing a language without opt-in can be a natural-language policy violation.
The guidance says to send screenshots 'as needed' whenever the user does not know the product or needs to 'see' it, which is a broad trigger that can cause the agent to send media in many ordinary conversations without a clear user request or tighter decision criteria. In context this is not code-execution or data-exfiltration dangerous, but it can lead to unnecessary or overly proactive content sharing, reduced user control, and policy/UX issues if screenshots are sent when not clearly warranted.