the-lancet-oncology
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external clinical oncology manuscripts and policy papers provided by the user.
- Ingestion points: User-provided draft manuscripts and oncology research papers processed in the 'When to trigger' and 'Scope & topic fit' sections.
- Boundary markers: The instructions lack specific delimiters or system-level instructions to the agent to treat the manuscript content strictly as data rather than instructions.
- Capability inventory: The agent is directed to access local resource files (source-basis.md, official-source-map.md) and perform live searches on official Elsevier/Lancet domains to verify submission instructions.
- Sanitization: There are no defined procedures for validating, filtering, or escaping content found within the user-provided manuscripts before processing.
Audit Metadata