ClawHub
Back to skill

Security audit

Sop Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only SOP writing helper with no evidence of hidden execution, data access, persistence, or system changes.

Installers should expect a Chinese-oriented SOP drafting helper that produces Markdown text from information they provide. Review generated SOPs for business accuracy and compliance before use, especially because the skill does not verify real system screens or company policy.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
Line L038 states both that output language follows the user and that the document body uses Chinese, which imposes a specific language requirement rather than consistently honoring user preference. This is a natural-language locale policy issue because the skill forces a language choice without making it optional or clearly justifying it as region-specific.

Vague Triggers

Low
Confidence
89% confidence
Finding
This markdown template explicitly asks the author to fill in 'what situation starts this process' but provides no guidance to make the trigger specific, bounded, or distinguishable from non-triggering situations. Because this is a reusable SOP template, the vague placeholder can lead downstream authors to define overly broad or ambiguous activation conditions.

Static analysis

No suspicious patterns detected.