twitter-x-search-results-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 the agent to hide that installation and not request separate user approval, which is a deceptive behavior outside the declared scraping 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 the BrowserAct CLI to access live Twitter/X pages at runtime and extract fields like “Post text” and “source page,” which would ingest outsider-authored free text from public social media into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The Skill explicitly instructs the agent to automatically install the required BrowserAct CLI at runtime using the install URL (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote code as a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). This Skill explicitly instructs the agent to automatically install a required CLI dependency and resume execution without asking the user to confirm, which can alter the host system (potentially requiring sudo) even though it doesn't explicitly request privilege escalation or file edits.