Back to skill

Security audit

Test

Security checks for vulnerabilities and agentic risk

Overview

This AList cloud-storage skill is mostly purpose-aligned, but it exposes credential-backed remote file operations with broad activation wording and no deletion safeguards.

Install only if you intend to let the agent operate on your AList server. Use a limited AList account where possible, verify paths before upload/move/delete actions, and require explicit confirmation before any rm command.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger text is broad enough to activate on generic file-management or cloud-storage requests, not just clearly scoped AList tasks. That can cause unintended skill invocation in unrelated contexts, increasing the chance of exposing credentials, performing file operations on the wrong backend, or steering users into a more privileged tool than necessary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises a destructive delete command (alist rm <path>) without any warning, confirmation guidance, or safety constraints. In an agent setting, this increases the risk of accidental or overly trusted deletion of remote files, especially if the skill is triggered automatically from natural-language requests.

Content

No source excerpt is available for this finding.