ClawHub
Back to skill

Security audit

box-legal-workflows-intake

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Box-based legal intake workflow, but users should verify its unpinned prerequisite skills before installing.

Before installing, verify the current Box skill sources and versions, then use the workflow only on the intended intake folder. Confirm attorney access, metadata writes, DocGen templates, shared-link audience, and expiration before allowing changes, and keep conflict, PEP, sanctions, risk, and legal decisions with the firm’s screening process and attorneys.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use the skill when the user mentions broad phrases such as 'client intake', 'client onboarding', 'new client review', 'intake documents', or 'engagement letters'. Several of these are common legal-workflow topics rather than narrowly scoped triggers, and the file does not provide exclusion conditions or negative examples to distinguish when this specific skill should or should not activate.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs users to install a dependency via npx skills add ... without pinning a specific version, commit, or immutable reference. This creates a supply-chain risk: a future upstream change or compromise of the referenced package/repository could alter the installed skill behavior and introduce malicious or unsafe actions.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

This line also references installation of a remote skill via npx skills add without an immutable version. Because the skill is for legal intake workflows that may process sensitive client information, an unpinned upstream dependency increases the risk that compromised or changed code could be introduced into a high-sensitivity workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.