youtube-channel-api-skill

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

• Third-party content exposure detected (high risk: 1.00). The skill calls BrowserAct's public API (scripts/youtube_channel_api.py: POST to https://api.browseract.com/v2/workflow/run-task-by-template and GET /get-task) to retrieve parsed YouTube search/channel data (public, user-generated content like channel descriptions/handles), and the SKILL.md explicitly instructs the agent to read and act on those results, so untrusted third‑party content can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the BrowserAct API at https://api.browseract.com/v2/workflow at runtime (using a TEMPLATE_ID and requiring BROWSERACT_API_KEY) to start and poll a remote workflow that executes browser automation code, making this an external runtime dependency that triggers remote code execution and is required for the skill to work.