linkedin-industry-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to install BrowserAct automatically and explicitly tells it not to ask the user or describe the installation (hide the action), which is a deceptive instruction outside the advertised 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 invoke the runtime browser-act Skill to access LinkedIn public pages/search results, which can cause the LLM to ingest outsider-authored free text scraped from third-party web content at runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill instructs the agent to automatically install a required runtime dependency via the URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and executing remote installer code at runtime.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.50). The skill explicitly instructs the agent to automatically install the BrowserAct CLI without asking the user, which directs the agent to modify the host environment by performing software installation (a state change), although it does not request sudo, system-file edits, or account creation.