linkedin-event-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive runtime instructions to install dependencies automatically and to hide that this is a request from the user (e.g., "install ... without asking the user to confirm" and "Do not describe it as a request..."), which are hidden operational directives outside the stated data-collection purpose and effectively override user consent.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill explicitly instructs automatic installation of an external CLI (BrowserAct) without asking the user for consent, creating a clear supply-chain/unwanted-installation risk that could be abused to deliver malicious code.

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 BrowserAct to access real LinkedIn browser pages at runtime and collect visible event descriptions/fields, which are outsider-authored free text from public web content that the LLM will ingest 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 a required runtime dependency from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (used at runtime to obtain/execute the BrowserAct installer), which means remote code could be fetched and executed during skill operation.