ClawHub
Back to skill

Security audit

Karpathy Guidelines

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent engineering-guidance checklist and does not contain executable code, hidden data access, persistence, or privilege-seeking behavior.

Installers should expect this skill to influence how an agent approaches substantive coding tasks by encouraging planning, local code reading, focused edits, and verification. It may add a little process to larger tasks, but no unsafe capability or undisclosed access was found.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction to 'Apply this skill to non-trivial software engineering work' is expansive and leaves 'non-trivial' to subjective judgment. Although examples are provided elsewhere, the file does not define clear exclusion conditions or a specific trigger list, which could cause over-application to ordinary coding tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.