Back to skill

Security audit

company-search-kimi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a public company research report template that uses search and page fetching, with no evidence of hidden execution, persistence, or data theft.

Installers should expect this skill to perform live public web searches and fetch pages about companies, including legal, business, hiring, and news records. Use it where Chinese structured reports are acceptable, and verify sensitive business conclusions against authoritative sources before relying on them.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content is written entirely in Chinese and strongly prescribes Chinese-language behavior without indicating that the agent should respect the user's language preference. This can cause unintended language switching, reduce usability, and create misunderstandings in multilingual or accessibility-sensitive contexts, though it is not a direct security exploit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The package description explicitly states the skill generates reports in Chinese, which can bias or force output language without user opt-in. This is dangerous because it can override user expectations, reduce usability for other audiences, and act as an undeclared behavioral constraint that may conflict with higher-level system or user instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.