novel-scene-writer
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional guidelines for creative fiction writing, such as 'Show, Don't Tell' and sensory integration.
- [PROMPT_INJECTION]: The skill acts on user-provided 'Scene Beats' to generate drafts. While it functions by interpolating this untrusted data into its output, its capabilities are confined to writing text files to a local
chapters/directory. No high-risk capabilities like network access or shell execution are present. - Ingestion points: Processes user-supplied 'Scene Beats' (SKILL.md).
- Boundary markers: Absent; instructions do not specify delimiters for user input.
- Capability inventory: File-writing to the
chapters/directory. - Sanitization: Absent; the skill relies on the underlying model's safety guardrails for content generation.
Audit Metadata