Security audit
Security checks for vulnerabilities and agentic risk
This YouTube helper is mostly coherent, but it asks agents to broadly auto-use a third-party service and persist API credentials in a way users may not clearly control.
Review this before installing if you care about privacy or credential control. Use it only when you intentionally want YouTube data routed through TranscriptAPI, and prefer manually setting the API key in a trusted secret manager instead of letting the skill create an account or persist credentials broadly.
The trigger language is unusually broad: it says to use the skill for any request where YouTube content would help, even if not mentioned explicitly. That can cause implicit invocation on ordinary research requests and send user queries or identifiers to a third-party API without a clear, specific user intent to use this service.
This file instructs the agent to obtain, handle, and persist TranscriptAPI credentials, including creating third-party accounts and completing OTP-based verification on the user's behalf. That behavior is materially outside the declared YouTube-data retrieval scope, creating an unjustified secret-handling and account-provisioning capability that could be abused for credential capture or unauthorized persistence of access.
The instructions tell the agent to persistently store a third-party API key so it survives future sessions and non-interactive shells, which expands the blast radius far beyond the immediate task. In the context of a YouTube helper skill, this creates unnecessary long-term credential retention and increases the risk of secret exposure, misuse by other workflows, or cross-session abuse.
The documentation explains how to call TranscriptAPI but does not clearly warn that user-provided search terms, video URLs, channel handles, playlists, and related metadata are transmitted to a third-party service. In a skill designed for broad automatic use, that omission creates a privacy and data-governance risk because users may not realize their inputs are being disclosed externally.
The guidance has the agent collect and store a sensitive API key without clearly warning the user that the secret may be retained persistently and available to future sessions. That omission undermines informed consent and can lead users to disclose credentials without understanding storage, reuse, and compromise risks.
No suspicious patterns detected.
