Podcastifier

• Outcome: Pass
• Latest audit: May 28, 2026, 12:54 PM
• Version:
  0.1.0

Overview

This is a coherent local podcast-generation skeleton with minor privacy and file-handling cautions, but no hidden network access, persistence, or destructive behavior in the artifacts.

Safe to install as a simple local skeleton, but do not feed confidential email/newsletter text into any future external TTS or Signal/Telegram integration unless you have reviewed that added code and the provider's data handling. Choose output paths deliberately because the script writes to the path you provide.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

with open(concat_list, 'w') as f:
            for w in wavs:
                f.write(f"file '{w}'\n")
        subprocess.run(["ffmpeg", "-f", "concat", "-safe", "0", "-i", concat_list, "-c", "copy", args.out], check=True)
        print(f"Output: {args.out}")
    finally:
        for w in wavs:

• Confidence: 85% confidence
• Finding: subprocess.run(["ffmpeg", "-f", "concat", "-safe", "0", "-i", concat_list, "-c", "copy", args.out], check=True)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README advertises optional Signal/Telegram delivery of generated podcast content but does not disclose that processed input may be transmitted to external messaging services. If users feed emails or newsletters containing sensitive or proprietary information into the skill, they may unknowingly exfiltrate that content to third-party platforms, creating privacy and compliance risks.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The documentation instructs users to wire in a TTS provider and supply an API key, but it does not clearly warn that the input text may be sent to an external TTS service for synthesis. Because this skill is specifically designed to process emails and newsletters, users may submit confidential communications without realizing the full text could be disclosed to a third party.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The skill description lacks a clear privacy and side-effect warning even though it processes potentially sensitive email/newsletter content and creates output files using TTS and ffmpeg tooling. Users may provide private content without understanding it will be transformed, stored, and passed through external tools or services, which can lead to accidental disclosure or retention of sensitive information.

VirusTotal

66/66 vendors flagged this skill as clean.