ClawHub
Back to skill

Security audit

diaper-stock-optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple diaper stock planning calculator with disclosed, local-only file output and no evidence of hidden access or unsafe behavior.

Install only if you are comfortable with a local Python script saving diaper plan JSON files in its own scripts/data directory. Avoid treating the diaper model as medical advice, and keep in mind that rerunning a plan with the same start date may replace the earlier saved plan.

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
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill instructs the agent to run a local Python script that writes plan JSON files to scripts/data/, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. Even though the described write target is local and appears operationally benign, undeclared file-write capability weakens least-privilege guarantees and can lead to unexpected filesystem modification if the skill is executed in a broader environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The plan command creates ./data/ and writes a plan file via open(path, "w"), which can overwrite an existing file with the same generated name. Although the saved path is printed afterward, there is no warning or confirmation before the write occurs in the code or docstring.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.