ClawHub
Back to skill

Security audit

Wip Repo Init

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward repo scaffolding tool that creates or reorganizes an ai/ documentation folder without hidden network, credential, persistence, or deletion behavior.

Install only if you want this ai/ documentation structure. Use --dry-run first on existing repositories, and avoid --yes unless you are comfortable with the existing ai/ folder being moved under ai/_sort/ai_old/.

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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 · SKILL.md (reported line 39)May include surrounding context.

text
wip-repo-init /path/to/repo              # scaffold ai/ in a repo
wip-repo-init /path/to/repo --dry-run    # preview without changes
wip-repo-init /path/to/repo --yes        # skip confirmation prompt

What happens

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 · templates/product/readme-first-product.md (reported line 68)May include surrounding context.

md
## How It Works

_The architecture at a level a new contributor can follow. Diagrams are fine. ASCII art is fine. The goal is: someone reads this section and can navigate the codebase without asking questions._

_Include:_
- _High-level data flow_

Static analysis

No suspicious patterns detected.