creative-writing-muse
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus entirely on creative writing workflow management. It references other internal sub-skills (e.g., /story-planning, /creative-writing-craft) for stance switching, which is a standard orchestration pattern in agent environments. No network requests, sensitive file access, or command execution patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data when defining author intent, emotional targets, and constraints (SKILL.md). While there are no explicit boundary markers or sanitization logic present for this data, the skill does not possess high-privilege capabilities or dangerous tools that could be exploited via malicious input. Standard agent-level safety guardrails remain the primary defense.
Audit Metadata