ClawHub
Back to skill

Security audit

Level Up Skill Tree

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk learning-planning prompt that reads its own documentation and does not access external services or sensitive data.

Installers should expect a conversational planning aid, not an automated assessment engine. It appears safe from a security standpoint, but its handler may only summarize the skill template rather than generate a complete skill tree by itself.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The implementation is a generic markdown/template reader and formatter. It loads metadata and section content from SKILL.md, extracts headings like purpose/workflow/output format, optionally includes user context, and returns a descriptive summary card. There is no logic related to learning goals, dependency graphs, progress assessment, upgrade criteria, or recommendation of an optimal growth path. The primary behavior is materially different from the declared purpose, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises a roadmap/planning skill that analyzes learning goals and produces a structured skill tree with progression logic. The supplied code chunk does not implement that functionality. Instead, it contains tests for helper functions and a handler, checking that metadata loads, prompt template headings exist, and the handler returns a descriptive text card referencing SKILL.md and the user's input. Based on this code alone, the actual behavior is documentation-oriented and validation-oriented, which is materially different from the declared purpose.

Content

No source excerpt is available for this finding.

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.

Static analysis

No suspicious patterns detected.