ClawHub
Back to skill

Security audit

企业-核心供应链波动预警

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed supply-chain research workflow that generates risk reports and does not include code, persistence, credential access, or hidden actions.

Install this if you want Chinese-language supply-chain volatility reports for companies. Be aware it may activate for broader company-outlook questions unless you phrase requests clearly, and it relies on current web sources whose quality should be checked.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions are phrased as broad business questions such as whether a company is stable or has good prospects, which can match many ordinary finance or company-analysis requests beyond the narrow intended supply-chain use case. This increases the chance of over-activation, causing the agent to invoke a specialized workflow unnecessarily and potentially bias, over-collect, or over-analyze user requests in ways the user did not intend.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

All user-facing description, triggers, and output instructions are written as mandatory Chinese-language behavior, and the file does not state that the skill is China-only or otherwise region-restricted. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.