inkos-story-review
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided data in the form of book chapters and prose for review. While this creates a surface for indirect prompt injection, the skill lacks access to sensitive capabilities or external network resources that could be exploited. The risk is minimized by its focus on analytical and creative writing tasks.
- Ingestion points: Processes user prose and chapters referenced in
SKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are utilized in the prompt instructions.
- Capability inventory: Limited to text analysis, scoring, and providing revision advice.
- Sanitization: No explicit sanitization of user-provided content is defined.
Audit Metadata