novel-research
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web and the local file system to provide research for novel writing, which introduces a surface for indirect prompt injection attacks.
- Ingestion points: External content from
web_searchresults and local text files within thenovel/directory. - Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions found within the researched data.
- Capability inventory: The skill instructions mention performing web searches and writing results to files in the
设定/(Setting) directory. - Sanitization: The skill lacks mechanisms for sanitizing or validating external data before processing and storing it.
Audit Metadata