Text To Podcast

PassAudited by ClawScan on May 1, 2026.

Overview

This appears to be a straightforward text-to-speech podcast generator, with expected notes around installing Python packages, using an OpenAI API key, and sending selected text to OpenAI.

Before installing, be comfortable with running a local install script, installing Python dependencies, providing an OpenAI API key, and sending the text you convert to OpenAI. Check where the installer creates the .env file so your API key is stored where you expect.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing the skill may modify your Python environment and depends on the current packages served by PyPI.

Why it was flagged

Running the install script pulls third-party Python packages into the local environment without pinned versions or a lockfile. This is expected for an OpenAI TTS tool, but users should be aware of the dependency install.

Skill content

pip3 install openai python-dotenv --quiet

Recommendation

Install in a virtual environment if possible, and consider pinning or reviewing package versions before running the install script.

Low

#ASI03: Identity and Privilege Abuse

What this means

Using the skill can incur OpenAI API usage and depends on protecting the API key.

Why it was flagged

The tool uses an OpenAI API key to call the TTS service. This is purpose-aligned and no credential leakage is shown, but the key grants access to the user's OpenAI account and billing.

Skill content

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
...
client = OpenAI(api_key=OPENAI_API_KEY)

Recommendation

Use a revocable API key, avoid sharing the .env file, and monitor OpenAI usage if converting many or long files.

Low

#ASI07: Insecure Inter-Agent Communication

What this means

Any text you convert may be transmitted to OpenAI for processing.

Why it was flagged

The contents of the user-selected text file are sent to OpenAI's speech API as input. This is the core TTS behavior and is disclosed, but it matters for private or confidential text.

Skill content

text = read_text(filepath)
...
response = client.audio.speech.create(
            model=model,
            voice=voice,
            input=text,

Recommendation

Do not convert confidential, regulated, or private documents unless you are comfortable with OpenAI processing that content under your account terms.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

The OpenAI key placeholder, and potentially the key if edited there, may be stored outside the skill's own directory.

Why it was flagged

Because install.sh is located in the skill directory, setting BASE_DIR to the parent of SCRIPT_DIR can create the .env file one directory above the skill folder. This appears to be a scoping/configuration issue rather than hidden behavior.

Skill content

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
BASE_DIR="$(dirname "$SCRIPT_DIR")"
...
cat > "$BASE_DIR/.env"

Recommendation

Check the exact .env path printed by the installer and prefer keeping credentials in the skill-specific directory or exported only for the session.