Back to skill

Security audit

dundun-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese legal-risk review prompt with broad activation language, but it does not include code, data access, persistence, or hidden behavior.

Install this only if you want a Chinese-language legal-risk review persona for contracts and business legal questions. Treat its output as informational, check jurisdiction-specific law, and consult a licensed lawyer before relying on it for important legal decisions.

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
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s trigger criteria are extremely broad and mandatory, causing it to activate on nearly any mention of legal topics. This can override normal routing and user intent, leading to unnecessary disclosure of sensitive legal content to the skill and increasing the chance of inappropriate, overconfident, or mismatched legal guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written to operate in Chinese and presents a fixed persona/output style without offering language choice. If invoked for users in other locales, it can degrade comprehension, cause misunderstanding of legal nuances, and increase the risk of users acting on advice they do not fully understand.

Content

No source excerpt is available for this finding.