Back to skill

Security audit

legal-advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable legal-advice skill whose sensitive document review is expected for its stated purpose, though users should limit what confidential material they share.

Use this skill only for appropriate legal-support tasks, share the minimum necessary documents, redact privileged or personal information where possible, and involve qualified counsel for regulated, high-risk, or jurisdiction-specific 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to review highly sensitive legal, contractual, employment, IP, and privacy-related content, but it does not warn users before collecting or analyzing such materials. Without an upfront warning, users may disclose privileged, confidential, or regulated information unnecessarily, increasing the risk of data exposure, mishandling, or improper processing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation section is broad and underspecified, causing the skill to activate for loosely related legal or business contexts without clear boundaries. In a legal-advisory skill, that ambiguity increases the chance of unnecessary access to sensitive contracts, employment records, compliance materials, or privacy documentation, and may lead users to rely on the skill outside intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.