novel-writer
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts with the WPS Note platform to store and retrieve story data. It does not access sensitive system files, environment variables, or hardcoded credentials.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-provided story ideas and content retrieved from notes. This is consistent with the primary functionality of a writing assistant and does not involve malicious intent. * Ingestion points: User input for story ideas; note content retrieved via search_notes and read_note (SKILL.md). * Boundary markers: None explicitly specified for separating instructions from note content. * Capability inventory: Note creation and editing (create_note, batch_edit), image insertion (insert_image) (SKILL.md). * Sanitization: No explicit sanitization or validation of input from notes is described.- [COMMAND_EXECUTION]: The skill uses specific, well-defined tools for note management and image generation within its execution environment. It does not attempt to execute arbitrary shell commands or system-level scripts.
Audit Metadata