ClawHub
Back to skill

Security audit

clause redraft

Security checks for vulnerabilities and agentic risk

Overview

This is a contract-clause rewriting helper with clear legal disclaimers and no hidden network, storage, persistence, or privilege behavior, though one trigger phrase is broader than ideal.

Reasonable to install if you want contract-clause drafting help. Treat outputs as drafting suggestions, not legal advice, avoid sharing highly sensitive contract text unless you trust the runtime, and be aware that the broad Chinese trigger for "rewrite this sentence" may activate this skill for non-contract editing prompts.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
93% confidence
Finding

The description includes broad trigger phrases such as '改合同', '改写这句话', and '条款润色' without clear boundaries on scope or required contract context. In an agent routing system, this can cause the skill to activate for general rewriting requests or legal-text-adjacent prompts, leading users into unintended legal drafting assistance and increasing the chance of overreach or unsafe handling of sensitive contractual content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase at line 28 ("改写这句话") is broad enough to match routine editing or paraphrasing requests that are not specifically about contract clauses. This can cause the legal drafting skill to activate outside its intended scope, leading to unnecessary collection or processing of sensitive text and increasing the chance of users receiving legal-style redrafts in contexts where that is inappropriate.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/redraft-templates.md (reported line 196)May include surrounding context.

General Provisions Templates

Template: Assignment

Problematic: "Cannot assign without consent"

Balanced Version:

text

Static analysis

No suspicious patterns detected.