Security audit

Voice Transcribe

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate transcription purpose, but it tells the agent to run a user-specific local script that is not included in the reviewed artifact while processing potentially private audio.

Review this before installing. Only use it for audio you are allowed to send to OpenAI, avoid confidential or regulated recordings unless approved, and verify the referenced transcribe script yourself because it is not included in the reviewed skill package.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill directs users to send audio files to OpenAI for transcription but does not disclose that potentially sensitive voice content will be transmitted to a third-party service. In this context, voice memos may contain personal, confidential, or regulated information, so the lack of notice and consent can create privacy and compliance risk.

Static analysis

No suspicious patterns detected.