Back to skill

Security audit

产业-产业机会识别

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language industry research/reporting skill that relies on public web information and does not include code execution, persistence, credentials, or hidden data handling.

Install this skill if you want Chinese-language industry resource mapping reports based on public web research. Users who need another output language or non-China-focused framing should confirm the agent can translate or adapt the report, and should treat the generated business recommendations as decision support rather than verified professional advice.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description defines the skill’s purpose, triggers, and behavior only in Chinese. This creates a language/locale constraint for users without documenting that the skill is region-specific or providing any language selection, which matches the policy’s language-choice concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The main instruction block, required analysis flow, and output template are all specified exclusively in Chinese, with no alternative language path or opt-in mechanism. Because the file does not clearly justify a China-specific compliance or regional scope, this is a natural-language locale policy issue rather than a mere stylistic choice.

Content

No source excerpt is available for this finding.