hashnode

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to connect to Hashnode and use actions like "Get Post", "List Posts", "Get User", and "Add Comment" (see the "Popular actions" section), which fetch and act on public, user-generated content from Hashnode — untrusted third-party content that the agent will read and could use to drive subsequent actions.