Back to skill

Security audit

PM Toolkit - Excalidraw - "Messy Thoughts" to "Visual Spec" in 30 seconds.

Security checks for vulnerabilities and agentic risk

Overview

This skill generates local Excalidraw PM diagrams from user-provided product notes, with disclosed local file creation and no evidence of network access, persistence, credential use, or destructive behavior.

Install only if you are comfortable with the skill writing a temporary JSON file and an Excalidraw output file locally. Use a dedicated folder, review the output path before running it, and delete only the temporary input file the skill created.

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
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill performs file creation and deletion and instructs running a local script, but it declares no explicit tool scope or permissions. That mismatch can cause an agent or user to invoke filesystem-capable actions without clear boundary-setting, increasing the chance of unintended writes to sensitive locations or execution in contexts that should have been restricted.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The workflow tells the agent to create a temporary JSON file and later delete it without warning the user that data will be written to disk and removed afterward. Even if the content is ordinary PM data, silent filesystem side effects can surprise users, leave sensitive business information on disk if cleanup fails, or delete the wrong file if the temp path is not tightly controlled.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.