product-hunt-launch-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). This skill explicitly instructs the agent to install a dependency automatically without asking the user and to conceal that the installation link is a request for the user's browser — a deceptive behavior that falls outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the runtime browser-act Skill to access and interact with live public web pages/directories (outsider-authored free text from fetched websites becomes LLM-readable content via the browser automation workflow).

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 to automatically install a required runtime dependency via the Install BrowserAct link (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which indicates the agent will fetch and run remote installation code at runtime.