story-long-write
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the skill's 125 files reveals a legitimate and well-architected framework for managing long-form creative writing projects. The skill's behavior is consistent with its stated purpose.
- [COMMAND_EXECUTION]: Utility scripts such as scripts/chapter_candidate.py and scripts/story_doctor.py utilize subprocess.run() to invoke internal linting and consistency tools. These operations are confined to the skill's own directory and do not involve the execution of arbitrary or externally sourced commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user novel text and benchmark data. It employs rigorous boundary markers and multiple deterministic validation layers to ensure that input data does not interfere with the agent's instruction following or the integrity of the writing process.
Audit Metadata