Back to skill

Security audit

Moot Court AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned moot-court simulator, but users should treat uploaded case materials as sensitive because it relies on external LLM providers.

Install only if you intend to simulate Chinese civil procedure and are comfortable using DeepSeek and DashScope/Qwen with your materials. Redact sensitive personal, financial, privileged, or confidential case details unless you have authorization to send them to those providers, and verify the missing Lobster workflow/setup before relying on the skill.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to supply case files and also requires external LLM API keys, but it does not disclose that uploaded legal materials may be sent to third-party model providers. Because court and dispute documents often contain sensitive personal, financial, or strategic information, this omission can cause unintended confidentiality and privacy exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description specifies a full Chinese civil court hearing and the rest of the document reinforces a fixed Chinese legal/procedural context. This appears to impose a specific language/locale mode without stating that users can opt in or choose another locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.