ClawHub
Back to skill

Security audit

Legal Compliance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a template generator for startup legal and compliance documents, with clear disclaimers and no hidden execution behavior.

Use this as a drafting aid only. Review generated documents for your jurisdiction and product details, and have a qualified lawyer review anything before production use; be aware the broad trigger terms may make it activate for general compliance questions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description contains a long list of broad trigger phrases such as 'compliance', 'legal requirements', and 'data protection' that can match many general user requests, causing this skill to activate outside its intended scope. Because the skill generates legal templates, over-triggering can steer unrelated conversations into legal/compliance guidance and increase the chance users receive inappropriate or overconfident template output in sensitive contexts.

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/legal-templates.md (reported line 30)May include surrounding context.

md
## Cookies and Tracking

We use:
- **Essential cookies**: Required for the product to function (no consent needed)
- **Analytics cookies**: [PostHog/etc.] to understand usage (requires consent)

You can reject non-essential cookies via the cookie banner.

Static analysis

No suspicious patterns detected.