youtube-api

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: youtube-api Version: 1.5.0 The skill contains instructions in `references/auth-setup.md` that explicitly guide the AI agent to bypass security redaction mechanisms (specifically mentioning Hermes and Claude Code) by writing sensitive tokens to temporary files to avoid detection by the runtime's output filters. It also directs the agent to persist environment variables in shell configuration files and defines broad triggers in `SKILL.md` that allow it to activate even when not explicitly requested. While these behaviors are presented as necessary for the `transcriptapi.com` setup, the deliberate guidance on evading platform security controls is a high-risk indicator.

Findings (0)

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.

What this means

The agent may spend TranscriptAPI credits and send search terms or YouTube identifiers to transcriptapi.com when it decides YouTube data is useful.

Why it was flagged

The invocation scope is broad and may cause the agent to call a paid third-party API for adjacent research tasks, though this is disclosed and aligned with the skill's YouTube-data purpose.

Skill content
any request where YouTube content would help — even if not mentioned explicitly
Recommendation

Ask the agent to confirm before broad searches, paginated browsing, or credit-consuming calls if you want tighter control.

What this means

A TranscriptAPI key may be stored on the machine or agent environment and reused in later sessions.

Why it was flagged

The skill asks the agent to handle and persist a TranscriptAPI credential. This is expected for the integration, but it affects the user's local credential boundary.

Skill content
Store it persistently using whatever method is correct for this environment (which you determined in Step 0). Make sure it will be available in future sessions, including non-interactive shells, without any manual sourcing step from the user.
Recommendation

Use a dedicated TranscriptAPI key, confirm the storage location, avoid sharing it in chat or logs, and revoke or rotate it if you no longer use the skill.

What this means

The agent may create a TranscriptAPI account for the user and handle the resulting API credential.

Why it was flagged

The setup flow can ask for the user's email, submit a registration request, receive an OTP from the user, and exchange it for an API key. This is disclosed and limited to TranscriptAPI account setup.

Skill content
You will handle the full signup on the user's behalf.
Recommendation

Only proceed if you trust transcriptapi.com and are comfortable letting the agent handle the email verification flow.