Back to skill

Security audit

Zksync

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a simple local reference script, but it is advertised as zkSync-specific while providing generic placeholder guidance that could mislead users.

Install only if you understand this is not a reliable zkSync reference. It does not appear to perform unsafe local actions, but its content is under-scoped and should not be used for blockchain, financial, compliance, deployment, bridging, wallet, or smart-contract decisions without independent authoritative sources.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill advertises itself as a zkSync reference tool, but the documented commands and descriptions are largely generic finance/compliance placeholders rather than zkSync-specific guidance. This is dangerous because users may rely on the skill for blockchain decisions under a false assumption of domain specificity, leading to incorrect operational, security, or compliance actions in a financial context.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file header and help text explicitly present the script as a zkSync reference tool. In practice, the implementation only prints generalized, reusable reference prose with placeholders like 'specialized tool/concept in the blockchain domain,' which contradicts the stated intent of providing actual zkSync reference information.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest says this skill should be used when working with zksync in blockchain contexts, implying domain-specific reference functionality. However, the commands output broad boilerplate text about formulas, regulations, risks, instruments, and checklists that is largely generic and not meaningfully tied to zkSync or even concrete blockchain operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.