Back to skill

Security audit

OpenClaw: trust validation

Security checks for vulnerabilities and agentic risk

Overview

The skill has a reasonable safety goal, but it asks to persistently change agent behavior and includes unsafe shell-command templates for memory-derived values.

Review this before installing. Only add the persistent OpenClaw system prompt rules if you want this behavior across sessions, and revise the command guidance to use structured arguments, quoted values, -- option termination, and workspace-bound path checks.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:36
Finding

Command and Option Injection Through Untrusted Memory-Derived Shell Arguments

Content
View full analysis
Remediation
View remediation
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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing natural-language instructions exclusively in Chinese, including the description and operational guidance. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation because users are not offered an alternative language or explicit choice.

Content

No source excerpt is available for this finding.