ClawHub
Back to skill

Security audit

Workspace Temp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed temp-file management guide that keeps agent-created working files under a session-specific workspace temp directory.

Before installing, confirm you are comfortable with a skill that reads OpenClaw workspace configuration, uses the session list, and copies user-specified external files into a workspace temp folder. Avoid routing secrets through it unless you are prepared to clean the temp directory afterward.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
This skill operates under strict safety constraints:

- **No Code Execution:** Does not execute arbitrary code, shell commands, or external programs
- **Isolated Write Scope:** All write operations restricted to `<workspace>/temp/<session_id>/` only
- **Read-Only External Access:** External files are only read and copied, never modified in place
- **Temporary Only:** Files are designed to be deleted; no permanent storage outside workspace
Confidence
80% confidence
Finding
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Session Persistence

Medium
Category
Rogue Agent
Content
This skill operates under strict safety constraints:

- **No Code Execution:** Does not execute arbitrary code, shell commands, or external programs
- **Isolated Write Scope:** All write operations restricted to `<workspace>/temp/<session_id>/` only
- **Read-Only External Access:** External files are only read and copied, never modified in place
- **Temporary Only:** Files are designed to be deleted; no permanent storage outside workspace
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.