weft-ai-language

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves helping the user write Weft programs and configure AI workflows, and mentions tools like WebSearch which retrieve external content, but the core runtime interaction is providing guidance and code snippets rather than continuously ingesting external untrusted feeds.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains instructions to clone an external repository via git and download setup scripts from external URLs, representing an inbound operational dependency from an unofficial source.