ClawHub
Back to skill

Security audit

box-legal-workflows-contract

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Box contract-review workflow, but users should review its broad trigger wording and unpinned dependency-install instructions before using it.

Install this only if you intend the agent to work with Box-hosted legal contracts. Before use, confirm any dependency installation, the target Box folder, template file, metadata fields to write, and any attorney collaboration or comments. Prefer pinned or reviewed versions of the prerequisite Box skills in sensitive legal environments.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad: it says to use the skill whenever the user mentions contract review, monitoring, metadata, renewals, or variance analysis, even without naming a specific Box tool. Overly broad invocation can cause the agent to activate this skill in contexts where Box access, document processing, metadata writes, or legal-workflow actions were not actually intended, increasing the risk of unintended data handling or action selection.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs the agent to install and execute a dependency via npx skills add ... without pinning a specific version or immutable commit. This creates a supply-chain risk: a later upstream change, compromise, or typosquatted resolution path could alter what gets installed and executed in a security-sensitive workflow handling legal documents.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

This line again directs runtime installation of a skill using npx skills add without a pinned version or immutable reference. Because the skill operates in a Box/legal workflow context with document access and metadata writes, executing unpinned external code increases the chance of unauthorized data access or altered behavior if the upstream package changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.