clawdhub

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow (e.g., search, install, update, publish) necessarily interacts with an external registry/website (default https://clawdhub.com or user-supplied --registry), and the LLM context would plausibly include free-form text from those outsider-authored pages/metadata when resolving results and changelogs.