lex

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow (“lex get” / “lex verify”) indicates the agent fetches and ingests retrieved legal context and official government links as readable text, which is outsider-authored free text from external web sources/pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's agent instructions and CLI commands (e.g., "lex verify" and template steps) explicitly instruct fetching external legal references at runtime—most notably N-Lex (https://n-lex.europa.eu/)—which will be injected into the agent context and therefore directly control prompts.