Security audit

AI Content Repurposer

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches its content-repurposing purpose, but batch mode can write outside the requested output folder and the docs do not clearly explain that user content is sent to OpenAI.

Review before installing. Use a dedicated OpenAI API key if possible, avoid processing confidential or regulated content unless your organization approves OpenAI processing, and only run batch config files you trust. Run it as a normal user, not with elevated privileges, and write outputs to a dedicated directory.

SkillSpector

By NVIDIA

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 (5)

Missing User Warnings

Low

Confidence: 92% confidence
Finding: The quick start encourages users to configure an API key for AI-powered transformations and later demonstrates URL-based content fetching, but it does not warn that input content and fetched URLs may be sent to external services or processed remotely. This can lead users to unintentionally submit sensitive blog, transcript, or podcast content to third-party systems, creating a privacy and data-handling risk even though it is not an exploit in the traditional sense.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README instructs users to configure an OpenAI API key and use network-backed transformations, but it does not warn that provided transcripts, blog text, podcast content, URLs, or batch job content may be sent to an external AI service for processing. This creates a real privacy and data-handling risk because users may submit confidential, copyrighted, regulated, or customer data without informed consent or understanding of third-party transmission.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly requires an OpenAI API key and shows direct API integration, which strongly implies user-provided transcripts, blog text, or podcast content will be transmitted to a third-party service. Failing to disclose this can cause unintended exposure of private, copyrighted, client, or regulated content, especially because the tool is marketed for broad business and agency use.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The usage examples repeatedly demonstrate writing outputs to files and directories, but the skill does not warn that specified output paths may overwrite or modify existing files. This creates a risk of accidental data loss or unintended modification, particularly in batch mode where many outputs may be written at once.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: User-provided transcripts and scraped blog content are sent to a third-party AI API, which can expose sensitive or proprietary data without clear consent, disclosure, or data-classification controls. In a content-processing skill, users may reasonably provide unpublished drafts, internal podcasts, or confidential transcripts, making silent external transmission a real privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/converter.js:11