ClawHub
Back to skill

Security audit

Legal

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only legal reasoning template, but users should treat it as general information rather than a lawyer substitute.

Install only if you want a structured legal-information workflow. Do not rely on it for court deadlines, filings, criminal exposure, immigration, family law, large financial stakes, or jurisdiction-specific decisions without review by a licensed attorney.

A.I.G

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

SkillSpector

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

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises that it can handle 'any legal situation like a lawyer,' which overstates capability and encourages users to rely on generalized model output in high-stakes, jurisdiction-specific matters. This can mislead users into treating the skill as a substitute for licensed counsel, increasing the chance of harmful decisions based on incomplete or incorrect legal analysis.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Although the skill mentions having a disclaimer ready, it does not provide a strong, prominent warning that the output is not a substitute for a lawyer and may be incomplete, outdated, or jurisdictionally incorrect. In a legal-analysis skill, weak warnings materially increase the risk that users act on model output in time-sensitive or regulated situations without professional review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.