ClawHub
Back to skill

Security audit

Policy Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides a template for drafting internal business policy documents, with no code execution, persistence, credential access, or hidden behavior found.

Treat generated policies as drafts. Have qualified legal, HR, security, or compliance staff review them before adoption, especially for regulated areas such as GDPR, HIPAA, SOC 2, or ISO 27001.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README markets the skill as producing 'complete, enforceable' internal policies and references regulated domains like GDPR, HIPAA, and ISO 27001, but it does not warn that outputs may be inaccurate, incomplete, or unsuitable without legal/compliance review. This can cause users to adopt AI-generated policy text as authoritative, creating compliance gaps, unenforceable provisions, or regulatory exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction says 'When the user asks for a policy document' without narrowing scope, trigger phrases, or exclusions. This is broad enough to overlap with many ordinary requests and does not clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.