ClawHub
Back to skill

Security audit

Markdown TOC Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Markdown table-of-contents generator that only reads a user-specified file and writes back when explicitly run with the in-place option.

Install only if you are comfortable with the agent running a local Python script on Markdown files you specify. Use the non-in-place mode to preview the TOC first, and use --in-place only on files you intend to update.

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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs users to run a script that reads and can modify arbitrary Markdown files, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap: an agent may infer file read/write capability from the instructions without a bounded path or tool policy, increasing the chance of unintended file access or modification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.