ClawHub
Back to skill

Security audit

DEPRECATED - Bobo Session Cleanup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local OpenClaw session cleanup helper that scans session files and only directs cleanup after user confirmation, with one command-hardening caveat.

Before installing, confirm you are comfortable with a skill that inspects and may delete OpenClaw session files after approval. Prefer archive or move operations first, and if hard deleting, ensure filenames come from the scan output and are quoted or otherwise safely handled.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
在用户确认后删除孤儿文件：

```bash
rm ~/.openclaw/agents/main/sessions/<orphan>.jsonl
```

### B. 再处理过期会话（谨慎）
Confidence
89% confidence
Finding
The skill recommends a direct `rm ~/.openclaw/agents/main/sessions/<orphan>.jsonl` pattern using a placeholder derived from scan output, without showing any validation, quoting, or path confinement controls. If an orphan filename is attacker-influenced or improperly sanitized elsewhere, this can enable deletion of unintended files via path traversal, globbing, or shell metacharacter abuse.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This skill is user-invocable, but the primary usage instructions and safety steps are presented only in Chinese, while other metadata includes English text. The file does not offer language selection or state that the skill is region/language-specific, which can violate a language/locale policy requiring user opt-in or clear justification.

Static analysis

No suspicious patterns detected.