chapter-writing
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely within the local filesystem, reading and writing story-related markdown files. It does not perform network operations or execute external scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface that includes reading from story.md, character profiles, and plot files (SKILL.md). While no boundary markers or explicit sanitization steps are defined, the skill's capability inventory is limited to writing prose and updating local markdown indices, which poses no significant security threat. The interaction is focused on creative writing within a user-controlled project directory.
Audit Metadata