ClawHub
Back to skill

Security audit

Industry Research Report Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language industry research report generator with expected web research and PDF output steps, and no evidence of hidden, persistent, destructive, or credential-seeking behavior.

Install this if you want a Chinese-oriented industry due-diligence report workflow. Be aware that it may perform multiple web searches and generate a PDF, so for casual questions you may want to ask for a brief answer instead of a full report.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description includes broad trigger phrases such as '研究某行业', '行业分析', and '投资研究', which are common requests that could cause the skill to activate in situations beyond the author's intended scope. Over-broad activation can route ordinary conversations into unnecessary web-search and PDF-generation workflows, creating prompt-scope confusion and increasing the chance of unintended tool use or data handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file's natural-language instructions are written as if the skill will operate in Chinese by default, and the description targets Chinese report-generation behavior without any opt-in or alternative locale handling. This can violate language or locale policy when users have not explicitly chosen Chinese as the interaction or output language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The applicable-scenario section defines invocation conditions in very general terms like '快速了解一个陌生行业' and '呈现行业分析', without clear boundaries distinguishing when this skill should or should not run. This ambiguity can cause accidental activation for generic research requests, expanding the skill's operational footprint and raising the risk of unwanted tool calls and irrelevant report generation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill explicitly requires Chinese and English font choices, including Chinese fonts such as 宋体/黑体, but does not ask the user for locale or language preferences. This hard-coded formatting expectation may impose a specific language/locale convention without documented justification.

Content

No source excerpt is available for this finding.