ClawHub
Back to skill

Security audit

Legal

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable legal-operations guidance skill whose sensitive subject matter is disclosed and purpose-aligned, but users should still apply confidentiality controls and human legal review.

Install only in an environment approved for confidential legal work. Do not provide privileged, regulated, or unnecessary personal data unless that environment is authorized, and have a qualified human verify deadlines, citations, filings, trust-account actions, conflict checks, and client-facing communications before relying on them.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill is designed for legal operations involving highly sensitive client, matter, billing, trust-account, and discovery data, yet it provides no explicit safety guidance about confidentiality boundaries, privileged information, AI hallucination risk, or mandatory human verification before use in filings or client communications. In the legal context, omission of these warnings materially increases the chance that users will paste privileged or regulated data into the system or rely on unverified AI-generated legal content, leading to waiver, ethical violations, missed deadlines, or inaccurate court submissions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.