ClawHub
Back to skill

Security audit

excalidraw

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward local diagram generator that creates Excalidraw files and does not show hidden data access, persistence, or remote-code behavior.

Before installing, be aware that this skill will create or overwrite local diagram files in the current workspace. Use it for explicit diagram-generation requests, and review output filenames if working in a sensitive directory.

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 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
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The core functionality is related to Excalidraw generation, so the domain is aligned, but the declared description materially overstates how the skill works. The code is a file-based converter from structured diagram JSON to .excalidraw, not a natural-language-to-diagram generator. There is no NLP, prompt parsing, or general request interpretation. It also supports a limited set of diagram builders: flowchart, architecture, mindmap, and sequence. Therefore the description does not accurately represent the actual behavior, even though the output format and broad diagram purpose are similar.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to write diagram_input.json and produce an .excalidraw output file, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where file-writing behavior exists without clear sandboxing or path restrictions, increasing the chance of unintended writes or abuse if the skill is invoked in a sensitive workspace.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger guidance is very broad (create, draw, visualize, show the flow of, etc.), which can cause this skill to activate for many generic requests that do not actually require file generation. Over-triggering increases the chance of unnecessary file writes, misrouting user intent, or invoking build steps in contexts where a safer plain-text response would have been sufficient.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.