ClawHub
Back to skill

Security audit

Contract Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This contract-review skill is a local text-analysis tool that reads user-supplied contract files and prints summaries, risks, and comparisons without network access or persistence.

Install only if you are comfortable with contract contents and excerpts being displayed in your terminal or agent transcript. Use it on text files you intentionally provide, and avoid running it in shared or logged environments for confidential agreements.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill exposes executable commands and indicates capabilities consistent with reading files and environment data, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an avoidable trust gap: an agent may grant broader access than necessary, increasing the chance of unintended file or environment data exposure if the backing scripts are invoked with unsafe inputs or broader runtime privileges.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The compare command prints excerpts of differing contract paragraphs directly to stdout, which can expose sensitive legal, commercial, or personal information in terminals, logs, CI output, or shared environments. In a contract-analysis skill, the processed documents are especially likely to contain confidential data, so echoing content without redaction, consent, or a privacy warning creates a real confidentiality risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase "legal document review" is broader than the rest of the listed contract-focused triggers and could overlap with requests about many non-contract legal documents. Because the skill is named and described as a contract analyzer, this broader phrasing creates ambiguity about when the skill should activate versus when a more general legal-review capability would be intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Multiple commands emit Chinese-only or mixed Chinese-first interface text such as headings, labels, and checklist content, but the script does not provide a language selection mechanism. This can violate a language/locale policy when users are forced into a specific language without opt-in or clear region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.