captions

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill fetches YouTube video captions via transcriptapi.com based on user input, and YouTube video transcripts contain outsider-authored text ingested at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to make HTTP requests to transcriptapi.com and execute remote registration and verification flows; however, transcriptapi.com is an arbitrary third-party domain without established official or first-party provenance, constituting a weak operational dependency.