wk-scope-guard

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

• Third-party content exposure detected (medium risk: 0.30). This skill’s required runtime workflow ingests outsider-authored free text indirectly via the tool payload’s tool_input.command (and file_path for Edit/Write) sent to the PreToolUse hook, so a user can supply arbitrary command strings that the hook lexes/tokenizes at runtime.