ghost-admin-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs generating JWTs from Admin API keys and shows examples that embed the raw key/token (e.g., SDK init with key "{id}:{secret}" and curl headers with "Authorization: Ghost {token}"), which would require the agent to accept and insert secret values verbatim into commands or code.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the agent will browse and read site content via the Ghost Admin API (e.g., api.posts.browse(), GET /admin/posts/, requesting formats=html,lexical) and create/edit posts from arbitrary HTML (api.posts.add(..., {source: 'html'})), which consumes user-generated content from external Ghost sites that could contain untrusted instructions.