Security audit

YouTube Distiller

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do its stated video-summarization job, but it exposes an API key and stores/sends transcript-derived content with limited disclosure.

Review before installing. The publisher should remove and rotate the exposed MiniMax key, clearly disclose that transcripts are sent to MiniMax, and make SumoNoteBook syncing more explicit or opt-in. Do not use this skill on private or sensitive videos unless external AI processing and local persistence are acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Context-Inappropriate Capability

High

Confidence: 99% confidence
Finding: The document contains a hardcoded third-party API key in plaintext, which is a real secret exposure. Anyone with access to this file can reuse the credential to consume the external service, incur charges, access associated account resources, or pivot into other connected workflows if the key is overprivileged.

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The README explicitly documents that the tool reads a MiniMax API key from environment variables and writes generated content to a local output directory, but it does not warn users that video-derived content may be sent to a third-party API or that generated/transcribed data will persist on disk. This creates a real security/privacy risk because users may process sensitive URLs or content without understanding data retention, local exposure, or third-party disclosure implications.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly states it will fetch subtitles from external platforms and use the MiniMax API, but it does not warn users that content will be transmitted over the network to third-party services. This creates a real transparency and privacy risk because users may provide private, unlisted, or sensitive video URLs without understanding that the transcript or related content may leave the local environment.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly sends transcript or video-derived text to an external AI provider but provides no user-facing warning, consent flow, or data-handling notice. This creates a real privacy and compliance risk because users may submit copyrighted, sensitive, or personal content without understanding that it will leave the local environment.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The script sends extracted subtitle text to a third-party AI service without a clear consent prompt, opt-in, or prominent warning at execution time. Subtitle content may contain personal, sensitive, proprietary, or regulated information, so automatic external transmission creates a real privacy and compliance risk in this skill context.

Ssd 3

Medium

Confidence: 93% confidence
Finding: The code forwards raw extracted subtitle text to an external LLM and then stores generated output into local note repositories without any filtering, redaction, or content-safety checks. This can propagate sensitive data, prompt-injection content, or harmful text into both an external processor and persistent internal knowledge stores, increasing privacy and integrity risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.