refine-story
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of Markdown files (SKILL.md and various reference guides). There are no scripts, binaries, or configuration files that execute logic on the host system.
- [SAFE]: The skill's instructions are limited to reading from and writing to local files in the
.claude/stories/and.claude/refinements/directories. It does not access sensitive system paths, hardcode credentials, or attempt to communicate with external servers. - [SAFE]: No prompt injection or obfuscation patterns were detected. The use of instructional terms like 'IMPORTANT' and 'CRITICAL' is strictly confined to the context of project management and story quality assessment.
Audit Metadata