story-short-write
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local utility scripts including
scripts/check-ai-patterns.js,scripts/check-degeneration.js, andscripts/normalize-punctuation.js. These tools are used to validate prose quality, detect repetitive AI-flavor patterns, and ensure consistent formatting throughout the story. - [COMMAND_EXECUTION]: The instructions include a shell command loop designed to locate a valid Python interpreter (
python3,python, orpy) to execute a character-counting snippet. This is used to provide accurate cross-platform word counts during the writing process. - [PROMPT_INJECTION]: The skill uses highly structured instructions and formatting rules defined as 'highest priority' to guide the agent's behavior. These are designed to maintain narrative consistency and quality rather than bypassing security filters or overriding core safety guidelines.
- [SAFE]: Analysis of the included scripts and instructions did not reveal any hardcoded credentials, unauthorized network exfiltration, or attempts to access sensitive system files. All external references target the author's own repository or trusted creative writing resources.
Audit Metadata