snowflake-novel-writer
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of structural guidelines and creative writing references. No malicious behaviors such as data exfiltration, privilege escalation, or persistence mechanisms were found. The instructions are focused solely on assisting the user with fiction writing.
- [NO_CODE]: The skill does not include any Python, Node.js, or shell scripts. All functionality is delivered through Markdown-based instructions and local reference documentation, eliminating risks associated with malicious code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied story 'fragments', 'settings', and 'outlines' (as noted in the Workflow and Interaction Mode sections of
SKILL.md). While this constitutes a data ingestion surface, the risk is minimal as the skill lacks executable tools or network capabilities that could be abused. The structured steps of the Snowflake method serve as a functional boundary for the input.
Audit Metadata