Back to skill

Security audit

Swarm Janitor

Security checks for vulnerabilities and agentic risk

Overview

This cleanup skill is purpose-aligned but deserves review because it promotes deleting OpenClaw session data, including force and no-archive examples, while the package does not include the script it tells users to run.

Install only if you are comfortable with a tool that can delete OpenClaw session files and handle transcript archives. Use dry-run first, verify the session path and retention settings, avoid --no-archive or --force unless you have separate backups, and be aware that the reviewed package did not include the Python cleanup script referenced by the documentation.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documentation includes destructive cleanup commands such as `--clean --no-archive` and `--force` with only minimal cautionary language, which can normalize irreversible deletion of session data. In a maintenance skill whose stated purpose is to delete files under user session directories, insufficient warnings materially increase the chance of accidental data loss by operators or automation.

Static analysis

No suspicious patterns detected.