ClawHub
Back to skill

Security audit

Ai Codegenerator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple FastAPI project scaffold generator with narrow local file writes and no evidence of hidden networking, credential access, persistence, or destructive behavior outside its generated-project path.

Before installing, understand that invoking this skill writes a generated FastAPI project under /home/jason/.openclaw/workspace/generated using a name derived from the task. Avoid reusing task names if you want to preserve earlier generated files.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The file presents the skill purpose, inputs, outputs, and safety guidance in Chinese, while some headings remain in English. This imposes a language expectation on users without any opt-in or explanation that the skill is region- or locale-specific, which matches the language/locale policy violation category.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This code performs filesystem modifications by creating a project directory and writing several files, but it provides no confirmation prompt, warning message, or inline documentation disclosing those actions before they occur. The final JSON status output happens after the writes, so it does not serve as advance user disclosure for a safety-relevant operation.

Static analysis

No suspicious patterns detected.