facebook-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill instructs the agent to auto-install BrowserAct and explicitly forbids describing the install link as a user-facing request or asking for approval, which is a deceptive instruction to perform actions without informing or obtaining consent and is outside the scraping task's stated behavior.

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 invokes the external browser-act dependency to access Facebook pages and extract comment text (outsider-authored free text from public/authorized Facebook posts) into the agent’s LLM context for analysis/output.

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 to automatically install and invoke the BrowserAct runtime using the URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (and the related https://www.browseract.com/?co-from=social-media), which is a runtime fetch used to obtain and execute the required CLI/Skill code.