T05 · Unauthorized Access and Privilege Escalation
- Location
scripts/utils/validator.js:11- Finding
Unrestricted Local File Selection Enables Sensitive File Upload
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a real cloud video transcription tool, but it needs Review because it can upload arbitrary local files and fetch arbitrary URLs despite narrower documentation.
Install only if you trust the publisher and service, and only run it on explicit video/media inputs you have reviewed. Avoid giving it sensitive local paths or untrusted URLs, especially in cloud or enterprise environments, until it adds media validation, URL/domain restrictions, upload-domain allowlisting, size limits, and clearer data-handling disclosures.
scripts/utils/validator.js:11Unrestricted Local File Selection Enables Sensitive File Upload
scripts/utils/validator.js:3Server-Side Request Forgery Through Unrestricted URLs and Redirects
scripts/utils/upload.js:10Server-Controlled Presigned URL Can Redirect Local File Uploads to Arbitrary HTTPS Hosts
scripts/utils/helper.js:27Unbounded Remote Downloads Allow Disk and Network Resource Exhaustion
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
If the implementation only validates URLs and local file paths rather than performing the advertised transcription and content-generation tasks, the documentation overstates capabilities and may mask what the skill truly does. This is risky because orchestration systems may auto-select the skill for broad user intents, giving an untrusted or incomplete component access to user-supplied paths and URLs without delivering the claimed business function.
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
4. 同时传入文件路径与任务ID,优先执行 `--id`,忽略 `--file`
5. 无自定义 prompt 时,默认完整转录视频全部文字
| 用户自然语言指令 | 自动生成命令 |
| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| 视频提取 https://example.com/video.mp4 中的文字 | `node scripts/video2text/index.js --file "https://example.com/video.mp4"` |
| 把本地 /path/to/your/video.mp4 改成小红书风格的文案 | `node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "改写成小红书风格的文案"` |
The skill declares access to an environment variable (GUAIKEI_API_TOKEN) but does not define an explicit tool/permission scope such as allowed tools or permissions. That creates ambiguity about what execution capabilities the skill is intended to use and weakens reviewability, especially for a command-type skill that may run code and handle local files or network inputs.
The trigger scope is very broad and covers many generic content-processing intents, making accidental or overbroad invocation likely. In an agent environment, overly broad routing can send unrelated user content, URLs, or local file paths to a third-party-integrated skill without sufficiently specific user intent.
The instructions explicitly tell the AI to prioritize this skill for broad natural-language requests, which can override safer routing decisions and cause unnecessary third-party data exposure. This is particularly risky because the skill accepts URLs, local paths, and free-form prompts, so mistaken invocation can expand both data handling and execution scope.
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
当用户用自然语言下达指令时,按以下映射生成命令,保证识别与执行一致:
| 用户自然语言指令 | 生成的命令 |
| ---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| 提取 https://example.com/video.mp4 里的文字 | `node scripts/video2text/index.js --file "https://example.com/video.mp4"` |
| 总结这个视频的核心观点 https://example.com/video.mp4 | `node scripts/video2text/index.js --file "https://example.com/video.mp4" --prompt "总结这个视频的核心观点"` |
The package description advertises many loosely bounded use cases and input types, including local files, multiple third-party platform links, transcription, summarization, rewriting, translation, and content generation. Broad activation language increases the chance the skill is invoked in unintended contexts, causing over-collection of user content or execution on untrusted media/URLs without clear scope restrictions.
This file uses Chinese-only natural-language comments, parameter descriptions, operation labels, and error messages throughout, with no indication that the skill is region-specific or that users can choose another language. That creates a language/locale policy issue because the skill implicitly forces a specific language experience without opt-in or justification.
This JavaScript file contains user-facing comments, error messages, and help text entirely in Chinese, including the top-level description and all CLI guidance. Under the stated policy, forcing a specific language without offering a user choice or documenting a justified locale constraint is a natural-language policy violation.
This file implements a fully generic HTTP/HTTPS downloader with redirects, retries, resume support, arbitrary headers, optional request body, and caller-controlled filenames. That capability is broader than the skill’s stated purpose of Douyin transcript/copy extraction and can be repurposed to fetch arbitrary remote content, increasing the risk of SSRF-style access to internal resources or unauthorized downloading if any user-controlled URL reaches this class.
This JavaScript file contains natural-language content in comments and runtime status/error messages exclusively in Chinese, such as the function comment and multiple inlineLog strings. Because the skill does not provide any user opt-in, fallback, or documented justification for a Chinese-only locale, it violates the language/locale policy criterion.
Multiple user-facing error strings are hard-coded in Chinese, including request failures and token guidance. This enforces a specific language/locale without any opt-in, fallback, or justification, which matches the policy category for language/locale violations.
The file emits all user-facing warning and status messages in Chinese only, including the token misconfiguration notice and recovery instructions. This imposes a specific language on users without offering a language choice or documenting that the skill is intended only for a Chinese-speaking or region-specific audience.
The comment makes a strong privacy and retention promise that uploaded videos are not retained and are automatically deleted after transcription, but this file only performs an upload and contains no deletion, retention control, or verification logic. In a skill that handles user video content for transcription, this mismatch can mislead users and operators about how sensitive media is handled, creating privacy, compliance, and trust risk if files persist in storage longer than represented.
This file contains natural-language comments and error strings exclusively in Chinese, including the upload privacy statement and runtime error text. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation, and this file does not indicate that the skill is explicitly China-only or offers language selection.
The file presents all operational instructions, warnings, and examples only in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
This JavaScript file contains its descriptive comment and all user-facing status/error messages exclusively in Chinese. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is explicitly documented and justified, which is not present here.
The banner text is presented only in Chinese, which constitutes a natural-language locale choice embedded in the code. There is no indication here that the skill is region-specific or that users can opt into a different language, so this may violate language/locale policy guidance.