ClawHub
Back to skill

Security audit

Esi Protocol Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent legal drafting skill with sensitive intake questions, but no hidden execution, persistence, or data-sharing behavior.

Use placeholders where possible and avoid entering privileged content, unnecessary PII, credentials, real matter numbers, or confidential client-identifying details unless your firm's policies permit it. Attorney review is still required because the skill drafts legal documents but does not provide case-specific legal advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
90% confidence
Finding

The skill explicitly asks the user to provide litigation-sensitive information such as case identifiers, client side, claims/defenses, preservation actions, custodians, and data-source details, but it does not first warn the user not to paste privileged, confidential, or personal data into the chat. In a legal-discovery context, users are especially likely to provide protected matter details, so omission of a confidentiality minimization warning increases the risk of unnecessary disclosure into the LLM system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.