ClawHub
Back to skill

Security audit

Karpathy Wiki

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown wiki assistant that persistently edits a user-directed knowledge base, with no executable code or hidden external behavior found.

Install this only if you want the agent to maintain a persistent markdown wiki. Expect it to read relevant source notes and update wiki pages, index.md, and log.md during ingest or durable query work; ask for read-only answers when you do not want changes saved.

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description is broad enough to match many ordinary note-taking, research, summarization, and knowledge-management requests, which increases the chance the agent invokes it in situations the user did not intend. Because the skill is stateful and designed to modify a persistent wiki, over-broad activation can lead to unnecessary file reads/writes, silent persistence of transient analysis, and unintended changes to a knowledge base.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill repeatedly instructs the agent to update wiki pages, index files, and append to logs as part of normal operation, but it does not require an explicit user warning or confirmation before modifying persistent files. In practice, this can cause unexpected writes to a repository or local vault, creating integrity, privacy, and auditability issues if user queries or raw-source content are persisted without informed consent.

Static analysis

No suspicious patterns detected.