ClawHub
Back to skill

Security audit

Improve Doc

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-editing skill that can rewrite the markdown file you point it at, but the behavior is disclosed, interactive, and aligned with its purpose.

Install this only if you are comfortable with a skill that edits the original markdown file you provide. Use it on files in version control or make a backup first, and review each proposed section change before accepting it.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill performs a destructive overwrite of the user-supplied Path, but the main user-facing warning appears only after completion and not as an upfront explicit warning before write time. Even though the workflow includes gates and an abort path, silent or insufficiently signposted overwrite behavior can lead to accidental data loss or modification of important documentation files.

Instruction Override

High
Category
Prompt Injection
Content
> | Option | Type | Default | Description |
> |--------|------|---------|-------------|
> | port | number | 3000 | Server port |
> | debug | boolean | false | Enable debug mode |
>
> Now let's configure each one step by step...
Confidence
70% confidence
Finding
This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Self-Modification

High
Category
Rogue Agent
Content
1. **Build updated content** from accepted changes
2. **Preserve unchanged sections** exactly as they were
3. **Overwrite original file** with updated content

### Step 5: Report Results
Confidence
97% confidence
Finding
The skill explicitly instructs the agent to overwrite the original file at the provided Path. While this is core to the skill's purpose rather than malicious self-modification, it still grants the agent a file-writing capability that can alter user content and cause irreversible changes if the path is wrong, the analysis is flawed, or the session is interrupted.

Static analysis

No suspicious patterns detected.