webnovel-plan
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes bash and python commands to perform file system operations and manage project metadata. These operations are essential for its purpose of automating the novel planning workflow.
- [PROMPT_INJECTION]: The skill processes user-controlled files, creating an indirect prompt injection surface. This is a standard characteristic of tools that analyze user documents.
- Ingestion points: Data is read from files such as
大纲/总纲.md,.webnovel/state.json, and various story-setting markdown files. - Boundary markers: No explicit delimiters or safety instructions are used to separate the ingested content from the system prompt.
- Capability inventory: The skill can read local files, execute a local management script, and write output back to the project directory.
- Sanitization: No sanitization of the story content is performed before processing.
Audit Metadata