twitter-x-space-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive installation instructions that tell the agent to automatically install a dependency without user confirmation and to hide/avoid describing the installation request to the user, which is outside the scraping tool's stated purpose.

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 Twitter/X browser pages at runtime and extract “browser-visible chat samples, pinned messages, badges, and engagement context,” which are outsider-authored free text from public web content that can 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 treats the BrowserAct CLI/Skill as a required runtime dependency and instructs automatic installation from https://www.browseract.com/?co-from=social-media (and the installer redirect link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which indicates the agent will fetch and execute remote installation content at runtime.