ClawHub
Back to skill

Security audit

Tee Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a small tee-like utility whose file-writing behavior is expected, but users should know it overwrites files and its documented options are not actually implemented.

Install only if you want a minimal pipe-output saver. Treat it as overwrite-only: do not use it on important files unless you intend to replace them, and do not rely on the documented -a or multi-file behavior unless the implementation is fixed.

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
  • 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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script writes stdin content to a file at a user-supplied path or to the default file 'out.txt'. There is no confirmation prompt, logging/print statement about the write target, or inline documentation warning the user that input will be persisted to disk.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill documentation clearly states that the tool writes stdin to one or more files, but it does not warn that existing files are overwritten by default unless `-a` is used. In an agent setting, this omission can lead to unintended data loss if the tool is used on important paths or logs, especially when chained into automated workflows.

Static analysis

No suspicious patterns detected.