Back to skill

Security audit

Force To Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped importer that saves user-provided agent bootstrap files into a new workspace rather than modifying the active workspace.

Install this only if you want an importer that turns pasted agent markdown into a new OpenClaw workspace. Review the pasted AGENTS.md, SOUL.md, TOOLS.md, and any openclaw.json snippet before using the generated workspace, because the saved files may shape future agent behavior.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

The skill is designed to persist user-provided content by creating a new workspace directory and writing multiple files automatically. Even though it avoids overwriting the main workspace and restricts writes to a scoped area, it still performs durable filesystem changes from pasted input, which can preserve malicious or unsafe agent configurations for later use.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: force-to-agent
description: Extract AGENTS.md, SOUL.md, TOOLS.md, and an optional openclaw.json patch from pasted custom-GPT markdown, then create a new workspace-<agent> folder and write the files there instead of overwriting the current workspace.
metadata: {"openclaw":{"always":true,"emoji":"🧩"}}
---

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill's operative instructions, triggers, and response formats are entirely specified in Korean, with no indication that users may interact in another language or choose their preferred locale. This can violate language/locale policy because it constrains usage to a single language without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.