ClawHub
Back to skill

Security audit

Poster Layout Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple academic poster layout helper, with some overly broad wording but no evidence of hidden access, persistence, or data misuse.

Installers should treat this as a low-risk draft skill, but should narrow the description and When to Use text so it activates only for academic poster layout tasks. The included script is simple and local, but review any future version that adds file output or dependencies.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The description presents this skill as something to be used by other workflows for structured execution with explicit assumptions and output boundaries, implying a broader orchestration or planning utility. The actual code is narrowly focused on academic poster layout generation: it takes a poster size and section list, splits sections across two columns, adds fixed top/bottom elements, and prints JSON. There is no implementation of workflow structuring, assumption tracking, or explicit boundary management beyond ordinary function output. This is a material primary-purpose mismatch, though there are no suspicious undeclared permissions or resource accesses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description and 'When to Use' section repeatedly say to use this skill for 'other workflows' or 'other tasks' needing structured execution, explicit assumptions, and bounded output. Those phrases are generic and overlap with many ordinary tasks, making it unclear when this poster-layout skill should activate versus a different planning or structured-output skill.

Content

No source excerpt is available for this finding.