linkedin-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to install required dependencies automatically and explicitly tells it not to ask the user for confirmation or to describe the installation as a browser request, which is a deceptive instruction outside the 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 runtime browser-act Skill to access and interact with live LinkedIn/public pages, which can cause outsider-authored free text from those fetched web pages (e.g., profile content) to be ingested into the LLM context via the browser-extracted page text.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill mandates using and auto-installing the BrowserAct CLI at runtime via the provided installer links (https://www.browseract.com/?co-from=lead-generation and https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which means the agent will fetch and run remote installation code as a required runtime dependency.