ClawHub
Back to skill

Security audit

Poka Yoke Design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Poka-Yoke report-writing assistant with a disclosed local file output side effect and no evidence of hidden, persistent, network, credential, or destructive behavior.

Before using it in a sensitive repository or shared folder, choose an output directory or check for existing files with the same dated report names. The referenced helper script and knowledge file were not included, so report generation may require the agent to create the files directly or fail if it expects those resources.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly states it will generate output files in the user's current working directory, which is a real side effect affecting the local filesystem. While the filenames appear predictable and the feature is aligned with the skill's purpose, the lack of a prominent warning/confirmation can still surprise users, overwrite expected artifacts, or create files in sensitive repositories or shared workspaces.

Content

No source excerpt is available for this finding.