ClawHub
Back to skill

Security audit

Agent Builder

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill helps users build OpenClaw agent workspace files and its sensitive behaviors are disclosed, optional, and aligned with that purpose.

Install this if you want help generating or refining OpenClaw agent workspace files. Review any generated MEMORY.md, HEARTBEAT.md, AGENTS.md, and skill roster changes before use, because those files can shape future agent behavior and may persist across sessions.

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
90% confidence
Finding

The skill description is broad enough to match many requests about designing, improving, or configuring agents, which can cause the skill to activate when a narrower or safer skill would be more appropriate. In an agent-building context, unintended invocation can expose users to unnecessary file generation, policy-shaping behavior, or overbroad workspace modifications driven by the wrong capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.