ClawHub
Back to skill

Security audit

Text to Published Podcast RSS

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward Cast0 podcast publishing helper, but users should treat submitted text as externally uploaded and potentially public.

Install only if you intend to publish text through Cast0. Before creating an episode, confirm the content is appropriate for a public podcast feed and do not submit secrets, confidential documents, personal data, or copyrighted/internal material unless you have rights and approval.

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 (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill causes user-supplied text to be published as a podcast episode and exposed through a public RSS feed, but the description does not clearly warn that this is public distribution rather than a private TTS conversion. That omission can mislead an agent or user into sending sensitive, copyrighted, or internal content to a publicly accessible channel.

External Transmission

Medium
Category
Data Exfiltration
Content
## Create an Episode

```bash
curl -X POST https://api.cast0.ai/api/episodes \
  -H "Authorization: Bearer pk_xxxxx" \
  -H "Content-Type: application/json" \
  -d '{"title": "Daily Standup", "text": "Here is what happened today..."}'
Confidence
98% confidence
Finding
The literal HTTPS endpoint in the example corresponds to a real external transmission of content to a third-party system. Because this action creates and auto-publishes podcast episodes, misuse or misunderstanding can expose confidential or sensitive text beyond the intended audience.

External Transmission

Medium
Category
Data Exfiltration
Content
## Create an Episode

```bash
curl -X POST https://api.cast0.ai/api/episodes \
  -H "Authorization: Bearer pk_xxxxx" \
  -H "Content-Type: application/json" \
  -d '{"title": "Daily Standup", "text": "Here is what happened today..."}'
Confidence
98% confidence
Finding
The literal HTTPS endpoint in the example corresponds to a real external transmission of content to a third-party system. Because this action creates and auto-publishes podcast episodes, misuse or misunderstanding can expose confidential or sensitive text beyond the intended audience.

External Transmission

Medium
Category
Data Exfiltration
Content
Every podcast has a public feed URL (no auth):

```
https://api.cast0.ai/rss/FEED_TOKEN
```

Subscribe in any podcast app. New episodes appear automatically after generation.
Confidence
97% confidence
Finding
The skill documents that each podcast has a public, unauthenticated RSS feed, meaning generated episodes are accessible to anyone with the feed token. In context, this increases the chance of inadvertent disclosure because users may assume TTS generation is private when the output is actually published for public subscription.

Static analysis

No suspicious patterns detected.