ClawHub
Back to skill

Security audit

Openclaw Design Consult

Security checks for vulnerabilities and agentic risk

Overview

This design-consulting skill is mostly coherent, but it can persistently modify project guidance files without a clear final confirmation step.

Install only if you are comfortable with a design skill that may add or change DESIGN.md and append design rules to CLAUDE.md. Before using the write step, ask the agent to show the exact planned changes and get explicit approval, especially for CLAUDE.md.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly states that the user can 'directly talk about anything at any time' and frames itself as an always-on conversational consultant rather than a narrowly triggered workflow. That broad activation scope can cause the skill to engage outside its intended design-consultation context, increasing the chance it influences unrelated tasks or is invoked when file-writing and repo-inspection behaviors are not appropriate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to write DESIGN.md and append to CLAUDE.md, but it does not require an explicit warning or confirmation immediately before making those file changes. In practice, this can lead to unexpected repository modifications, including changes to high-influence instruction files like CLAUDE.md, without sufficiently informed user consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.