ClawHub
Back to skill

Security audit

Industry Insight - 行业洞察分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese industry-research assistant that uses web research to produce structured market analysis, with no hidden code, persistence, credential access, or destructive behavior found.

Install this if you want a Chinese-language workflow for structured industry research. Be aware it may activate on broad market-analysis requests and it relies on web results, so verify important business or investment conclusions against primary sources.

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
92% confidence
Finding

The trigger phrases are very broad and overlap with ordinary requests for market, industry, and research help, which can cause the skill to activate unintentionally for many unrelated conversations. In a multi-skill agent environment, this creates routing ambiguity and increases the chance the wrong skill handles user input, potentially causing unnecessary tool use and disclosure of external-search-derived content when the user did not explicitly request this workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description and tags indicate a Chinese-only interaction model, and the document consistently instructs responses in Chinese without any opt-in or alternative language option. Under the policy, forcing a specific language is a violation unless the user is given a choice or the locale limitation is clearly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are overly generic, including common terms like '行业分析', '市场分析', and especially the broad pattern '分析[行业名]'. This can cause the skill to activate for ordinary research requests that were not intended to invoke this workflow, increasing the chance of prompt hijacking of normal conversations, unwanted tool use, and response steering away from user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The title, triggers, and usage instructions are all in Chinese, and there is no indication that the user may choose another language for interaction or output. This can be read as a default language constraint without user opt-in, which may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.