llm-wiki-zero-to-working-wiki

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow ingests an “optional first source text or file path” from the user and then has the agent create wiki/sources/* (including extracted claims/entities) from that provided content, meaning outsider-authored free text can be directly consumed.