inkos-story-review
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and analyze user-provided prose and manuscripts, which introduces a potential vector for indirect prompt injection.
- Ingestion points: The skill explicitly processes user stories, chapters, and manuscripts for diagnosis and scoring as outlined in SKILL.md.
- Boundary markers: There are no instructions to the agent to use specific delimiters or to ignore instructions that might be embedded within the story text.
- Capability inventory: The skill gives the agent the ability to diagnose, score, and provide revision advice for content, which could be manipulated by malicious text in a manuscript.
- Sanitization: The skill does not implement any validation or sanitization logic to detect or neutralize instructions hidden within user prose.
Audit Metadata