ClawHub
Back to skill

Security audit

clean-air-room-planner

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward air-purifier planning tool that only keeps optional diary and filter-tracking data locally.

Install only if you are comfortable with a local JSON diary being created for PM2.5 readings, timestamps, notes, purifier state, and filter usage. Avoid putting sensitive household details in notes, and delete artifact/scripts/air_data.json if you want to clear stored history.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises executable commands that write persistent data (the pollution diary and filter-life tracker) but does not declare any tool scope or permissions boundary. That mismatch can lead an agent runtime to grant broader-than-expected file-write capability or perform writes without explicit user awareness, which is a real security issue even if the intended writes are benign application data.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script persists PM2.5 diary entries and filter-tracking data to a local JSON file without clearly informing the user where the data is stored or how long it is retained. While the data is not highly sensitive by itself, timestamps, notes, and usage patterns can still reveal household routines or occupancy habits if another local user or process can access the file.

Content

No source excerpt is available for this finding.