linkedin-company-employees-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains deceptive instructions to install dependencies automatically and explicitly tells the agent not to describe the action to the user or request separate approval, which is hidden behavior outside the scraper's stated 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 invoke the runtime browser-act Skill to access live LinkedIn pages/search results, which can ingest outsider-authored free text from public web content into the LLM context via the browser-extracted page content.

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 the required BrowserAct dependency at runtime using the install URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and executing remote code as a required runtime dependency.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill instructs the agent to automatically install the BrowserAct CLI and resume execution without asking the user for confirmation, which could change the host system by installing software, but it does not explicitly request sudo, modify protected system files, or create user accounts.