twitter-x-post-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly instructs the agent to install BrowserAct automatically without asking the user and to hide/avoid describing that installation or requesting separate approval, which is a deceptive directive 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). This Skill explicitly instructs automated installation of external tooling without user consent and directs the agent to conceal that installation, creating a deliberate supply-chain/backdoor risk that could enable unauthorized code execution or data exfiltration.

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 delegates to the outsider-authored public Twitter/X pages via the BrowserAct CLI (“Collect public Twitter/X posts from URLs…”, then “invoke the browser-act Skill” to access real browser pages), so the LLM can ingest scraped free-form post text from third parties.

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 at runtime to automatically install a required runtime dependency using this installer URL which would fetch and run remote installation content: https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main