Back to skill

Security audit

Paper Checking

Security checks for vulnerabilities and agentic risk

Overview

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.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:63
Finding

Execution of Mutable and Unverified Remote Payloads

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
guides/01-installation.md:101
Finding

Unpinned and Unverified NuGet Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

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.

Content

No source excerpt is available for this finding.