story-long-write
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform local file system operations using shell commands like
ls -laandfind. These are used for project management purposes, such as verifying that story chapters were correctly written to disk or locating specific files in the project structure. - [COMMAND_EXECUTION]: The workflow incorporates the use of specialized sub-agents (
story-explorerandstory-researcher) to assist with context retrieval and factual research. This usage is consistent with advanced AI agent platforms and supports the skill's primary function without introducing security risks. - [PROMPT_INJECTION]: The references include strict stylistic guidelines (e.g.,
anti-ai-writing.md) designed to improve the quality of generated fiction. These constraints are task-related and do not attempt to override safety protocols or force the model into an unrestricted state. - [SAFE]: All external references point to the author's own repository, and no evidence of data exfiltration, credential harvesting, or malicious persistence was found.
Audit Metadata