ClawHub
Back to skill

Security audit

Plan Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain markdown planning helper that creates and updates local plan documents, with no evidence of hidden execution, credential access, networking, or destructive behavior.

Installers should expect this skill to create or update local markdown files under plans/ for agent and human planning. Avoid putting sensitive personal or business details into those plan files unless you are comfortable storing them in the workspace.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says to use the skill when 'managing both AI agent execution workflows and human task plans in a unified structure,' but it does not define exclusions, explicit trigger phrases, or when simpler planning requests should not invoke this skill. Because this is a markdown skill description, the broad activation language may overlap with many ordinary planning or task-management requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.