Back to skill

Security audit

Huo15 Openclaw Simplify

Security checks for vulnerabilities and agentic risk

Overview

This is a code cleanup review skill that reads recent code changes and only edits after user confirmation.

Installers should be aware that generic phrases like code cleanup or refactor may route to this skill. Before accepting fixes, review the generated checklist and choose which items to apply, especially in large or dirty worktrees.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The alias list contains vague phrases like '简化代码', '代码清理', '重构建议', and 'code cleanup' that are common requests and overlap with normal conversation. In an agent environment, these broad aliases can cause accidental skill routing, leading to unnecessary codebase reads and modification suggestions outside the user's precise intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases include very broad, everyday language such as '简化一下', '重构一下', and 'code review 一下(偏重质量)', which can match ordinary user requests without clear scoping. This increases the chance of unintended activation, causing the agent to perform repository inspection and propose edits when the user may have intended a lighter-weight or different action.

Content

No source excerpt is available for this finding.