Back to skill

Security audit

crosscheck

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent, but it asks users to run an unpinned npm package with a wallet private key, which deserves manual review before installation.

Review this before installing. Use only a dedicated low-balance wallet, prefer a pinned and independently verified package version, avoid sending confidential drafts or sensitive source material, and understand that checks send content to an external service for paid review.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill instructs the agent to tell the human the draft was checked only if it passed, or otherwise merely disclose remaining issues. That creates an integrity and transparency problem because review failures can be concealed or ambiguously represented, allowing unsafe or unreviewed outputs to be presented without clear notice that the check failed.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

This is not just a documentation nit: it operationally instructs execution of remote code with live wallet-related environment variables. Even though the skill recommends a low-balance dedicated wallet, compromise could still steal funds, private keys, or sensitive document contents, making the issue materially dangerous in context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.