youtube-batch-transcript-extractor-api-skill

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and the script scripts/youtube_batch_transcript_extractor_api.py explicitly run a BrowserAct workflow to fetch YouTube video transcripts and metadata (public, user-generated content) and return/print those transcripts for downstream use, so the agent will ingest untrusted third‑party content that can materially influence its subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The script calls the runtime API at https://api.browseract.com/v2/workflow (using a TEMPLATE_ID) to start and poll a remote workflow, which executes code on BrowserAct and is a required runtime dependency for the skill.