Security audit

vox

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped wrapper for the Vox transcription CLI with explicit user-control requirements and no bundled executable code.

Before installing, confirm you trust the Vox CLI and npm package because the skill can guide a global CLI install and use Vox authentication. Use it only with media URLs or exact local files you intend to send for transcription, and avoid passing sensitive private media unless that fits your Vox account and data expectations.

A.I.G

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

SkillSpector

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 (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The document switches to Chinese-only guidance in the '来源与合集' section, which imposes a specific language for operational instructions. There is no indication that the user can choose their language or that this locale restriction is required for a region-specific skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.