T03 · Remote Payload Retrieval and Execution
- Location
SKILL.md:63- Finding
Execution of Mutable and Unverified Remote Payloads
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a legitimate Chinese-language plagiarism-checking guide, but it tells users to download and run unverified external code while processing sensitive documents.
Install only if you trust the external GitHub project and can verify the exact release or source you run. Prefer a pinned, reviewed version; avoid unverified precompiled binaries; use a contained Windows environment; restrict the input and output folders; and treat generated reports and progress files as sensitive records.
SKILL.md:63Execution of Mutable and Unverified Remote Payloads
guides/01-installation.md:101Unpinned and Unverified NuGet Dependency Installation
The manifest description and the main skill content are entirely in Chinese, and the document gives no indication that users may interact in other languages or choose a preferred locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
The guide recommends downloading and using a precompiled executable from Releases and elsewhere in the document shows running the binary, but it provides no instructions to verify provenance, checksums, signatures, or publisher authenticity. This creates a supply-chain risk: users may execute a tampered, spoofed, or replaced binary with full user privileges, especially because the skill is explicitly an installation guide encouraging execution.
The statement "文件内容应为简体中文" is a natural-language locale restriction. The file does not present this as an optional recommendation, offer a language choice, or explain a necessary region-specific constraint, so it appears to force a specific language without opt-in.
The quickstart instructs users to generate RTF reports and optional CSV statistics but does not warn that these outputs may contain sensitive document excerpts, filenames, and plagiarism-match metadata written to disk. In a plagiarism-checking workflow, users often process academic, corporate, or bid documents, so silent local persistence can lead to unintended disclosure through shared folders, backups, or later redistribution.
The guide states that configured keywords will be automatically deleted before duplicate checking, but it does not clearly warn users that their submitted text is being modified as part of processing. In a paper-checking context, removing institution names or other selected terms can materially change analysis results, mask true similarity, and mislead users about the integrity and reproducibility of the report.
The document describes automatic preprocessing that deletes abstracts, tables of contents, references, and all non-Chinese characters without a prominent warning about content removal or its effect on results. In this skill's context, that can silently exclude meaningful portions of a document, especially citations, formulas, names, or bilingual text, causing inaccurate plagiarism assessments and making the output unsuitable for users who expect full-document comparison.
The entire troubleshooting guide is written in Chinese and does not indicate that other languages are available or that Chinese is an intentional locale-specific constraint. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale limitation is explicitly documented and justified.
This file contains user-facing instructions and examples exclusively in Chinese, which can amount to a language-policy issue when no opt-in or alternative locale is provided. The policy specifically calls for flagging skills that force a specific language without user choice or justification.