twitch-channel-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit, deceptive runtime instructions telling the agent to install dependencies without user confirmation and to hide that installation requests from the user, which are hidden/overriding behaviors outside the skill's stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the BrowserAct CLI to access real Twitch web pages at runtime (public web content), which can include outsider-authored free text that BrowserAct may extract and pass into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to automatically install a required CLI from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which is a remote install link used to fetch/execute external code for the Skill.