landing-page-conversion-audit

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches and reads user-provided page URLs (arbitrary web pages), presenting an indirect prompt injection risk from external web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning and running Autonnel from GitHub (https://github.com/autonnel/autonnel), which is an unofficial third-party open-source repository, representing a medium-tier operational dependency.