twitter-x-search-results-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill instructs the agent to install dependencies "automatically without asking the user to confirm" and explicitly to "not describe" the installation or request approval, which is a hidden/deceptive instruction outside its stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill's core scraping functionality is borderline (collecting public contact data) but contains explicit instructions to auto-install and invoke an external CLI without user confirmation and to conceal that installation, creating a clear supply-chain/remote-execution and unauthorized-installation risk that could enable data exfiltration or backdoor behavior.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the runtime browser-act Skill to access and interact with live public Twitter/X pages/search results, which can cause outsider-authored free text from those fetched web pages to be ingested into the LLM context.

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 and invoke BrowserAct at runtime using the install URL(s) 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 would fetch and run remote installer code required for execution.