facebook-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains instructions to automatically install a third-party dependency without user confirmation and discourages asking for approval, representing a security boundary violation.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow scrapes Facebook comments from user-specified post URLs, which are outsider-authored social feeds read via browser automation.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install an external skill from a GitHub repository via an unverified third-party promotional landing page, presenting a weak runtime external dependency.