Back to skill

Security audit

Huo15 Claw Butler File Delivery

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper for sending user-requested files to a paired Claw Butler client, with no bundled code, persistence, or hidden behavior found.

Install only if you use Claw Butler file delivery. Agents should use it for files you asked to receive or files created during the current task, and should avoid pushing arbitrary local files or uploading sensitive large files to external storage unless you explicitly approve that transfer.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
95% confidence
Finding

The trigger list is broad and includes common multilingual phrases such as '下载', '导出给我', and 'send me the file', which can match many ordinary user requests outside the narrow intended context. This can cause the skill to activate unexpectedly and push files through a privileged delivery channel when another skill or safer default behavior should have handled the request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The primary heading and instructional content are presented in Chinese, while the file does not state that language choice depends on user preference or locale. This can violate language/locale policy when the skill is applied to users who have not opted into Chinese output.

Content

No source excerpt is available for this finding.