ClawHub
Back to skill

Security audit

Rm Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward file deletion skill, but users should treat it carefully because it permanently removes files and folders.

Install only if you want an agent-accessible permanent deletion utility. Use it on explicit, narrow paths, avoid broad globs and recursive force deletion unless you have verified the target, and do not rely on the documented interactive option because the included script does not implement it.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This skill describes permanent file and directory deletion, including recursive and force options, but does not prominently warn that actions are irreversible and can destroy large portions of the filesystem if misused. In an agent context, the absence of explicit safety guidance increases the chance of accidental destructive use, especially with examples like '-rf' that normalize high-risk invocation.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
This script permanently deletes files and directories immediately after parsing arguments, with no confirmation prompt, dry-run mode, trash/recycle-bin behavior, or safety interlocks. In an agent skill context, that makes accidental or mis-targeted invocation especially dangerous because a bad path, wildcard expansion, or misunderstanding can irreversibly destroy user data.

Static analysis

No suspicious patterns detected.