ClawHub
Back to skill

Security audit

Pywayne Adb Logcat Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small ADB logcat usage guide with no bundled executable code; its main issue is that it should warn users that device logs can contain sensitive data.

Before installing, understand that this skill helps read Android device logs through adb. Those logs may include app identifiers, URLs, debug messages, stack traces, or secrets, so avoid unnecessary persistence and redact sensitive lines before sharing. Do not rely on the documentation's statement that logs are automatically cleared when stopping the reader unless you verify the underlying library behavior.

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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
ADB logcat often contains sensitive information such as app identifiers, debug messages, tokens, URLs, stack traces, and occasionally user or device data. Omitting any warning about this can lead users to capture, display, or store logs insecurely, increasing the risk of unintended data exposure during normal use of the skill.

Intent-Code Divergence

Low
Confidence
76% confidence
Finding
The skill is described throughout as a reader that starts `adb logcat`, streams lines, and stops the process. Line L90 adds a stronger claim that logs are 'cleared automatically when process stops', which is materially different from simply terminating a reader and would imply an additional destructive operation such as `adb logcat -c`.

Static analysis

No suspicious patterns detected.