ClawHub
Back to skill

Security audit

smell-source-detective

Security checks for vulnerabilities and agentic risk

Overview

This is a local household-odor troubleshooting skill with disclosed local note logging and no evidence of hidden network, credential, or persistence behavior.

Install only if you are comfortable running a local Python script and, if using the log feature, avoid entering sensitive personal details because notes are saved locally in the skill folder until manually removed.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest focuses on ranking smell sources, danger screening, localization, and remediation guidance. This file additionally implements a logging feature that stores user-provided notes on disk in smell-log.json, which is behavior beyond the core diagnosis protocol described in the manifest.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The log command stores user-supplied freeform notes persistently on disk without an explicit warning, retention policy, or consent prompt. In context this is low severity because data remains local and the tool is household-focused, but users may still enter sensitive health, occupancy, or location details expecting an ephemeral assistant interaction.

Content

No source excerpt is available for this finding.