ClawHub
Back to skill

Security audit

Leo

Security checks for vulnerabilities and agentic risk

Overview

This is a simple personal-profile skill for Leo with no executable behavior, network access, credential handling, or hidden automation.

This skill appears safe to install as a personal information template. Users should understand it may answer broadly about Leo and that the included local path reveals where the skill is usually stored; replacing that path with generic update guidance would reduce unnecessary environment detail.

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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description says the skill provides queries about Leo's information, contact, work, projects, and cooperation, but it does not define specific trigger phrases, scope limits, or exclusion conditions. This is broad enough to overlap with common conversational requests like asking who Leo is or how to contact him, which could cause unintended invocation.

Skill Enumeration

Medium
Category
Agent Snooping
Content
### 使用说明

本技能是 Leo 的个人介绍模板。如需更新个人信息，请编辑 `~/.openclaw/workspace/skills/Leo/SKILL.md` 文件。

---
Confidence
84% confidence
Finding
The usage note exposes a concrete local filesystem path under the user's home directory, revealing the workspace layout and exact skill location. While not immediately exploitable on its own, this information can aid reconnaissance, prompt-targeting, or chained attacks that rely on knowledge of local file paths and installed skill names.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The manifest description and user-facing documentation are presented in Chinese only, with no indication that users can choose another language. This may violate a language or locale policy when the skill is used in a broader multilingual environment without explicit user opt-in.

Static analysis

No suspicious patterns detected.