sandbase

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md’s “Standard Workflow” uses discover→inspect→run via explicit tool calls (e.g., sandbase_discover/q and sandbase_run arguments), but the document itself does not describe any runtime step that automatically ingests third-party outsider-authored free text without the user first selecting/searching specific content endpoints.