Back to skill

Security audit

Excalidraw Handdraw

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Excalidraw diagram-generation helper that uses local Docker, browser automation, and file writes in ways that fit its stated purpose.

Install only if you are comfortable with a skill that can start or use a local Docker canvas service, run browser-based export JavaScript, move generated image files, and update Markdown where you ask it to. Give exact output paths and review any proposed file edits before applying them.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list contains broad, common phrases such as '画图', '创建图表', and '生成图表', which can match ordinary user requests and cause the skill to activate unintentionally. Because this skill can start Docker, run local commands, download files, move files, and modify Markdown content, accidental invocation expands the chance of unexpected local side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs moving generated files into arbitrary local paths and inserting image references into Markdown files, but it does not require user confirmation, path validation, or safety warnings. In context, this is more dangerous because the same skill also performs automated browser downloads and shell commands, so a misinterpreted request or crafted prompt could lead to unintended overwrites or modifications of repository files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.