novel-writer-cli
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
wpsnote-clitool to perform operations such as creating, reading, editing, and syncing notes within the WPS Notes environment. It also utilizes agen-imagesubcommand for character and scene visualization. These command executions are the core functionality provided by the vendor to facilitate the writing process. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data by reading existing content and logs from WPS Notes to maintain continuity.
- Ingestion points: Data is ingested from note content via
wpsnote-cli read,wpsnote-cli read-blocks, andwpsnote-cli search(SKILL.md). - Boundary markers: No explicit delimiters or boundary markers are defined in the instructions for the agent to use when interpreting retrieved note content.
- Capability inventory: The agent can execute a variety of
wpsnote-clisubcommands to modify note content and generate images. - Sanitization: The skill does not specify sanitization or validation routines for data retrieved from external note files.
Audit Metadata