01-scaffold-and-plan

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

• Third-party content exposure detected (high risk: 0.90). The skill's Execution Protocol Phase 1 explicitly instructs fetching the Antonella framework from a public GitHub repository (via composer create-project antonella-framework/antonella-framework or git clone https://github.com/antonella-framework/antonella-framework), which is untrusted third-party code that the agent would fetch and execute as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches the Antonella framework at runtime (git clone https://github.com/antonella-framework/antonella-framework or via composer create-project antonella-framework/antonella-framework), which downloads remote PHP code that the workflow then installs and executes (composer install / php antonella), making it a required runtime dependency capable of executing remote code.