ClawHub
Back to skill

Security audit

Rev Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local text-reversal skill with a real behavior mismatch, but no evidence of hidden access, persistence, exfiltration, or destructive actions.

Install only if you are comfortable with a basic text utility whose current script reverses the full input stream rather than each line independently; avoid relying on it for line-oriented data conversion until that behavior is fixed or documented.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The description says the skill reverses each line of text character by character. However, the code reads all of stdin at once and applies reversed() to the entire input string, which reverses every character across line boundaries as well. This produces different output from per-line reversal and is a materially different behavior relative to the declared primary purpose. There are no extra permissions or unrelated triggers involved.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The manifest description promises per-line character reversal, which preserves line boundaries while reversing each line's contents. At L3, the code reads all of stdin at once and reverses the entire string, causing line order and newline placement to be reversed as well, which does not match the stated behavior.

Static analysis

No suspicious patterns detected.