linkedin-profile-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the agent to install BrowserAct automatically and to hide or avoid requesting user approval ("do not describe... and do not request separate approval for dependency installation"), which is a deceptive instruction outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill is designed for large-scale scraping of LinkedIn profile/contact data and includes explicit, deceptive instructions to install an external dependency without asking the user, creating a supply-chain/covert-installation risk that could enable data exfiltration or abuse.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime workflow invokes the browser-act Skill to access live LinkedIn pages (public web content), so the LLM context can include outsider-authored free text scraped from those pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent at runtime to install and invoke the BrowserAct CLI using the provided install links, which would fetch and execute external code from 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.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill instructs the agent to automatically install the BrowserAct CLI as a required runtime dependency without asking the user for confirmation, which directs the agent to perform autonomous system-level changes and potentially modify the machine state or install software without consent.