facebook-event-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill explicitly instructs the agent to install a required dependency automatically and to hide or avoid asking the user for approval (e.g., "without asking the user to confirm" and "do not request separate approval"), which is a deceptive instruction outside the stated scraping purpose.

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 use BrowserAct to access user-supplied Facebook URLs/search results at runtime, which can cause the LLM to ingest outsider-authored free text from public web pages (e.g., event descriptions/comments) via the live browser workflow.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly tells the agent to automatically install a required runtime dependency by fetching from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which implies downloading and executing remote installer code that directly enables the agent's runtime behavior.