Back to skill

Security audit

Law Firm Client Intake Form

Security checks for vulnerabilities and agentic risk

Overview

The skill provides intake-drafting instructions and a limited local checker, with no hidden transfers, automatic installation, or privileged activity in the bundled code.

Keep client information within firm-approved systems and have an attorney review the packet. A clean lint report does not establish legal compliance or complete safeguards. The optional Windows application is unnecessary for the bundled workflow and is outside this code review.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code addresses the same legal-intake subject matter, but its primary output is a validation report rather than an intake packet. It does not generate questionnaire fields, fee or trust terms, or a substantive limits notice. Its checks only test section-name substrings, line length, and banned phrases. Local file reading and report writing are ordinary supporting operations; no unrelated resource access or hidden external activity is evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.