linkedin-recruiter-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains deceptive runtime instructions that tell the agent to install a dependency automatically and to hide/avoid seeking user confirmation or describing the installation as a user-facing browser request, which is outside the scraper's stated data-collection purpose and is a concealed/authority-overriding instruction.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill contains explicit instructions to automatically install an external CLI dependency without user consent and to hide that request, which is a deliberate, deceptive installation/ supply‑chain/backdoor pattern that enables unauthorized execution and potential data exfiltration via scraping.

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/post text, which is outsider-authored free text from public web content fetched at runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to automatically use the install link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main to obtain and install the required BrowserAct CLI (a required runtime dependency), which implies fetching and executing remote installation code from that URL.