Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple in-memory material library with no evidence of hidden access, persistence, external network use, or destructive behavior.
Review this as an incomplete, Chinese-language material-library prototype: it can search, version, and archive only records currently held in memory, while upload/storage is not functional through the command interface. Pinning dev dependency versions would improve reproducibility, but I found no hidden persistence, credential access, network calls, or destructive actions.
This markdown file documents actions that store files and update existing material versions, which can affect user data. Under the markdown-specific warning rule, the description should disclose that these actions create or modify stored content, but no such warning or caution is present in the skill description.
The skill's user-facing command descriptions, argument help text, error messages, and success messages are written only in Chinese. This imposes a specific language on users without any opt-in, alternative locale, or justification that the skill is intended solely for a Chinese-speaking or region-specific environment.
The manifest describes a material library that provides storage, retrieval, and version management. However, the exposed upload subcommand is documented as "上传素材" yet its execute handler always returns success: false with an error saying upload requires extra integration, so the advertised storage capability is not actually implemented through the skill interface.
The skill description and primary documentation text are written in Chinese, but there is no indication that language selection is optional or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill imposes a language without user opt-in or documented justification.
The natural-language description is presented only in Chinese, which can indicate a language/locale constraint without user opt-in. For a general-purpose package manifest, there is no accompanying note that the skill is intended only for Chinese-speaking users or a specific regional context.
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
"license": "MIT",
"dependencies": {},
"devDependencies": {
"@types/node": "^20.0.0",
"typescript": "^5.0.0"
}
}
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
"dependencies": {},
"devDependencies": {
"@types/node": "^20.0.0",
"typescript": "^5.0.0"
}
}
No suspicious patterns detected.