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
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:30 AM