novel-writer-cli

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing system commands via the wpsnote-cli utility to interact with the WPS Notes platform, including searching, reading, and editing notes.
  • Evidence: Usage of commands like wpsnote-cli find, wpsnote-cli read, wpsnote-cli create, and wpsnote-cli batch-edit throughout the documentation.
  • [PROMPT_INJECTION]: The skill's architecture involves reading existing note content to inform future writing, which presents a surface for indirect prompt injection if note data contains instructions intended to manipulate the agent's behavior.
  • Ingestion points: Note content is retrieved from the local environment and WPS cloud via wpsnote-cli read and wpsnote-cli read-blocks (referenced in SKILL.md).
  • Boundary markers: No explicit delimiters or safety instructions are defined to separate user-provided note content from the agent's internal instructions.
  • Capability inventory: The skill has the ability to execute CLI commands and perform write operations to the user's notes.
  • Sanitization: The skill encourages the use of structured formats and the --json-args parameter when calling the CLI tool to minimize command injection risks during data interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 09:42 AM