Back to skill

Security audit

Workspace Cleaner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent workspace-cleaning tool, but it can rewrite or delete persistent agent control files with broad subjective criteria and limited rollback detail.

Install only if you are comfortable letting the skill reorganize persistent OpenClaw workspace state. Before approving any run, ask for a full diff, backups, explicit archive destinations, and a separate confirmation before BOOTSTRAP.md or any behavioral/safety instruction is deleted.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:19
Finding

Unsafe Modification and Deletion of Persistent Agent Control Files

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly performs workspace optimization by rewriting bootstrap files, archiving content, and potentially deleting files, but the top-level description does not warn users that it may modify or remove persistent workspace data. This can mislead a user into invoking the skill without understanding the scope of destructive changes, increasing the risk of unintended data loss or persistent state alteration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction to delete BOOTSTRAP.md after confirmation omits an explicit warning that deletion is irreversible and may remove information the user still needs. Even though the skill requires confirmation before execution, the confirmation prompt template does not specifically disclose file deletion risk, so consent may not be adequately informed.

Content

No source excerpt is available for this finding.