Back to skill

Security audit

Legal Advisor Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a plain legal-information skill with no code, tools, persistence, or hidden data access, though users should treat its legal output as informational and verify it with a licensed attorney.

Install only if you want general legal-information assistance. Do not rely on it as a substitute for a licensed attorney, especially for deadlines, court filings, criminal matters, employment disputes, or jurisdiction-specific rights; verify current law and citations independently.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation phrases are overly broad and map to very common legal-help terms, which can cause the skill to activate in situations beyond its intended scope. In a high-risk domain like legal advice, over-triggering can lead users to receive authoritative-sounding, jurisdiction-sensitive guidance without sufficient qualification or routing to safer handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction contains Chinese text ("核心诉求") within otherwise English guidance, which introduces an implicit language expectation without user opt-in or explanation. The file does not state that the skill is bilingual or region-specific, so this may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.