ClawHub
Back to skill

Security audit

Litigation Hold Notice Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a legal drafting skill that stays focused on preparing draft litigation-hold materials for counsel review, with one minor scope inconsistency around release-notice drafting.

Before installing, treat this as a drafting aid only: do not paste unnecessary confidential names or identifiers, ensure a supervising attorney reviews all output, and be cautious with the hold-release notice option unless counsel has already authorized release criteria and timing.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

This is a stronger instance of the same contradiction: the skill both forbids releasing a hold and invites the user to have it prepare a hold-release notice. In this context, inconsistent instructions are risky because they can mislead legal staff into using the skill beyond preservation scope, increasing the chance of spoliation or sanctions if a release is drafted or used before counsel has formally approved release criteria.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill creates a policy contradiction: it says it must not lift or release holds, yet explicitly offers to draft a hold-release notice. In a legal-preservation workflow, even drafting release language can operationally enable premature termination of preservation obligations if users treat the draft as endorsed guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The tone options include a fixed locale choice of "standard (formal, US English)" rather than offering language or locale selection. This is a natural-language policy concern because it prescribes a specific locale in the generated output without explicit user opt-in or a broader language choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.