scientific-literature-researcher
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from scientific publications and experimental data sources, which creates a surface for indirect prompt injection.
- Ingestion points: The skill retrieves data from published literature and experimental sources as outlined in the research workflow in SKILL.md.
- Boundary markers: There are no explicit markers or instructions defined to isolate the external research content from the agent's internal reasoning or system instructions.
- Capability inventory: The skill does not possess capabilities for file writing, network exfiltration, or subprocess execution.
- Sanitization: The instructions do not specify any methods for sanitizing or filtering the content retrieved from research papers before it is processed by the agent.
Audit Metadata