twitch-clip-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit instructions to install dependencies automatically and to avoid presenting the installation as a user-facing request (i.e., "do not describe it as a request" and "without asking the user to confirm"), which is a deceptive directive outside the core scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow invokes the BrowserAct CLI to access live Twitch web pages at runtime, so outsider-authored free text from public web content (e.g., clip titles/descriptions/comments visible on Twitch) can be ingested into the agent’s LLM context via the BrowserAct page-extraction path.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly treats the BrowserAct CLI as a required runtime dependency and instructs the agent to automatically install it from the provided URL(s) (e.g., https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main and https://www.browseract.com/?co-from=social-media), which implies fetching and executing remote installation code at runtime.