ClawHub
Back to skill

Security audit

agent-builder

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only helper for creating OpenClaw agent workspace files, with no code execution, credential handling, or hidden network behavior found.

Install only if you want help creating or revising OpenClaw agent workspace files. Review generated agent files before use, confirm autonomy and ask-before-destructive/outbound-message rules, and avoid storing secrets or private chat logs in optional memory files.

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
Confidence
88% confidence
Finding
The skill description is broad enough that an agent router may invoke it for many generic requests about designing or modifying agents, even when the user did not explicitly ask to generate workspace files or alter agent behavior. Over-broad matching can cause unintended use of a powerful configuration-generating skill, which may lead to unsafe agent definitions, accidental guardrail changes, or workflow confusion in higher-autonomy environments.

Static analysis

No suspicious patterns detected.