ClawHub
Back to skill

Security audit

科研课题成果汇编

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language research compilation helper that guides web-supported writing and Word export without hidden access, persistence, or credential handling.

Install this if you want a Chinese academic research-outcome compilation workflow. Users who need another language, a simpler one-off summary, or strict control over web research should state those preferences clearly before invoking it.

A.I.G

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad enough to match ordinary requests about summarizing or organizing research, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it may route user tasks into a workflow that performs web enrichment, structured document generation, and downstream docx actions without sufficiently explicit user intent for that specialized behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill hardcodes Chinese-language output conventions and stylistic rules without checking or preserving the user's preferred language. This is a vulnerability in the sense of unsafe scope/behavior control: it can produce incorrect-language outputs, mishandle multilingual source material, and reduce user control over how data is processed and presented.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The secondary trigger list repeats vague phrases like organizing a research topic or generating a research report without constraints on document type, workflow stage, or desired output. This increases the chance of accidental invocation and can override more appropriate skills, causing unintended data handling, web lookups, or content transformation in contexts where the user only asked for a simpler task.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file title and all instructional content are presented only in Chinese, which constitutes a language/locale constraint in natural-language content. The document does not offer an alternative language, opt-in choice, or state that the skill is intended only for a Chinese-language or region-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The title and throughout the document prescribe a specific Chinese-language academic writing standard as a universal norm, rather than as an optional locale-specific template. Because the guidance does not state that it is intended only for Chinese-language outputs or offer an opt-in choice, it can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.