linkedin-people-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to install BrowserAct automatically without asking the user and to conceal that installation (e.g., "do not describe it as a request..."), which are hidden/deceptive directives that go beyond the skill's stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the runtime browser-act Skill to access live LinkedIn pages and extract visible profile/search content, which is outsider-authored free text from public web pages fetched at runtime.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent at runtime to automatically install and invoke BrowserAct using the external installer URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=lead-generation), which would fetch and run remote installation instructions/code that control the agent's runtime behavior.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs the agent to automatically install the BrowserAct CLI and dependencies without asking the user for approval, which directs the agent to modify the host environment (install software) autonomously and therefore risks changing machine state without consent.