ClawHub
Back to skill

Security audit

OpenClaw Workspace Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, local, read-only OpenClaw workspace auditor with no evidence of network access, persistence, destructive actions, or hidden instructions.

Install only if you want an agent to inspect the current OpenClaw workspace and include local file/path health information in its report. Review the report before following any cleanup or reorganization suggestions, since the skill itself is designed to advise rather than fix automatically.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (9)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
python scripts/scan_workspace.py --root <工作区根> --report

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/readme/hero.svg (reported line 7)May include surrounding context.

text
<rect width="1200" height="360" rx="20" fill="#0d1117"/>

  <!-- left: title block -->
  <g id="title-block" transform="translate(56 40)">
    <text x="0" y="44" font-family="ui-monospace, SFMono-Regular, Menlo, monospace" font-size="20" letter-spacing="4" fill="#8b949e">OPENCLAW · AGENT SKILL</text>

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README uses broad natural-language triggers such as asking the agent to 'audit the workspace' or 'see whether the workspace is messy,' which can cause the skill to activate in contexts broader than the author likely intended. Even though this skill is described as read-only, overbroad activation increases the chance of unintended workspace scanning, unnecessary disclosure of workspace metadata in responses, or invocation when the user meant a casual discussion rather than an actual audit.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented trigger list includes short, generic phrases that are common in ordinary conversation and not uniquely tied to this workspace-auditing skill. The file does not provide exclusion conditions or negative examples to clarify when these phrases should not invoke the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The README suggests invoking the skill with "audit the workspace" or "health-check the workspace" without stating clearer scope boundaries or exclusion conditions. While somewhat domain-related, these phrases are still broad enough that an agent could match them in general conversation about workspace status.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The usage section repeats a single broad trigger phrase without constraints or disambiguation, reinforcing opportunistic activation from ordinary conversation. In agent systems, repeated broad invocation language can make routing less precise and may lead to the skill scanning local workspace contents when the user only asked a general question about organization or cleanliness.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The SVG contains Chinese text alongside English branding and descriptions, but it does not indicate that the user can choose the display language or that the asset is intended for a Chinese-speaking audience. Under the language/locale policy, forcing or assuming a locale without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The comment and code explicitly state that stdout is forcibly reconfigured to UTF-8 for all runs. This is a natural-language locale/encoding policy choice imposed by the skill without offering the user a choice or documenting it as an optional behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.