Dual-Host Daily Podcast Generator

• Outcome: Review
• Latest audit: May 29, 2026 at 9:22 PM UTC
• Version:
  1.0.0

Overview

This skill is purpose-aligned, but it can automatically publish generated podcast content to public feeds and external services with limited review and credential-safety guidance.

Install only if you are comfortable with generated scripts and audio being sent to Fish Audio, uploaded to S3/RSS, and optionally posted to messaging platforms. Use dedicated least-privilege AWS credentials and a non-sensitive bucket, keep API keys out of source files and logs, review generated content before publishing, and test manually before enabling cron.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The publish and delivery steps send generated content, podcast metadata, and potentially identifiers such as owner email, hosting URLs, and messaging content to third-party services like S3, podcast platforms, and chat tools, but the skill does not warn users about this data transfer. This can lead to unintentional disclosure of sensitive or regulated content, especially in a fully automated cron-based workflow.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The configuration requires a `FISH_API_KEY` and external voice IDs, indicating use of a third-party TTS provider, but it does not disclose that podcast scripts and voice segments will be transmitted to that provider for synthesis. Because the skill generates full conversational content, this omission can expose proprietary, personal, or compliance-sensitive material to an external processor without informed consent.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The script sends arbitrary podcast script text to a third-party TTS provider without any consent prompt, warning, or data-classification check. In this skill's context, the input may contain unpublished content, proprietary prompts, or sensitive material, so silent remote transmission creates a real confidentiality and compliance risk even though the behavior appears functionally intended.

External Transmission

Medium

• Category: Data Exfiltration

Content

return segments

def tts(text, voice_id, output):
    resp = requests.post(API_URL,
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json"

• Confidence: 96% confidence
• Finding: requests.post(API_URL, headers={ "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" }, json=

VirusTotal

63/63 vendors flagged this skill as clean.