voice-style
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a custom CLI tool named
storyto perform various project tasks such as prose analysis (story prose), dialogue checking (story voices), and reindexing (story reindex). These operations are constrained to the local project environment.\n- [DYNAMIC_EXECUTION]: Instructions are provided to run Node.js scripts from relative paths (../story-maintenance/scripts/story.js) or user-identified checkout paths (<checkout>/bin/story.js) as a fallback mechanism. The skill explicitly cautions against using the Bun runtime to avoid the risk of unintended code execution from local configuration files likebunfig.toml.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external text (drafted chapters and style sheets). It incorporates an explicit safety directive instructing the agent to treat imported or fetched text as data for analysis and never as instructions, reducing the risk of indirect prompt injection attacks.
Audit Metadata