Back to skill

Security audit

Clean Filename

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local filename-cleaning utility, with the main risk being that directory or recursive use can rename many files in place.

Use --dry-run first, especially with directories or --recursive, because applying changes can rename many files and may break links or references that depend on the old names.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly shows directory-wide and recursive usage but does not warn that it will rename many files in place, which can cause disruptive bulk changes, break references, and create accidental data-management issues. In this context, the danger comes from insufficient disclosure rather than obviously malicious functionality, making it a genuine safety/documentation weakness.

Content

No source excerpt is available for this finding.