ClawHub
Back to skill

Security audit

Editorial Chief Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed editorial workflow that may create review-ready Obsidian article files, but it shows no hidden code, credential use, auto-publishing, or persistence.

Before installing, be aware that this skill is designed to stage final article files and image assets inside an Obsidian vault. Confirm the exact vault folder and whether existing files may be overwritten before using it on important content.

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
  • 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 (4)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly directs delivery into the user's real Obsidian publication directory, which creates a real-world side effect on user files without an explicit safety gate, confirmation step, or warning at the point of capability declaration. In an agent setting, this increases the risk of unintended modification, overwrite, or staging of publishable content in a live vault, especially if the vault path is resolved automatically.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Not allowed:
- drifting off topic
- replacing fixed examples or changing the audience without approval

### 5.3 Style-optimization agent
Allowed:
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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Not allowed:
- drifting off topic
- replacing fixed examples or changing the audience without approval

### 5.3 Style-optimization agent
Allowed:
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.

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The only listed publication channel examples are WeChat Public Account and Xiaohongshu, which strongly suggests a fixed locale/platform context. The file does not explicitly offer users a language or locale choice, nor does it clearly document that this is a region-specific workflow justified by scope, so the natural-language instructions risk forcing a specific locale context by default.

Static analysis

No suspicious patterns detected.