Security audit

Voicescape Skill V1.1.1

Security checks for vulnerabilities and agentic risk

Overview

The onboarding features are clearly disclosed, but the example can approve unexpected wallet transactions because it does not verify what the server asks it to sign.

Use a dedicated wallet holding only minimal funds. Before running the own-keys example, require local verification that the actual transaction matches the approved registration, including its destination, arguments, value, and fees. Keeping the private key local does not prevent an unintended signed payment. Published identity and page data are permanent and public.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: examples/self-claim-own-keys.mjs
Finding: Remote transaction bytes are executed without binding them to the approved registration
Content: View full analysis
Impact

An adversarial MCP provider can present an innocuous registration preview but return a transfer debiting the configured operator account to an attacker-controlled account. The local client can authorize and submit that transfer without exposing the private key itself.

SkillSpector

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 (1)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, mcp.

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Static analysis