adding-service-documentation

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md, METADATA.md, IMAGES.md) explicitly instructs the agent to fetch and extract metadata and logos from public GitHub locations (e.g., https://github.com/coollabsio/coolify/tree/main/templates/compose and raw.githubusercontent.com URLs) and to consult service websites/GitHub READMEs, which are open/public third‑party sources that the agent is expected to read and that can materially change its documentation actions.