linkedin-sales-navigator-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to automatically install a runtime dependency and explicitly tells it not to request user approval or describe the link as a browser request, which is a deceptive instruction to hide actions outside the scraper's stated data-collection purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill contains explicit instructions to stealthily install an external CLI without user consent and to automate collection/export of contact data, which indicates deliberate potential for supply-chain/backdoor abuse and data exfiltration.

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 LinkedIn pages and extract visible profile/activity text, which is outsider-authored free-form web content that the LLM will ingest via the browser automation workflow.

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 and invoke the BrowserAct CLI at runtime using 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, which will fetch and execute remote installation code the skill relies on.