preprint-search
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external preprint servers, which creates a surface for indirect prompt injection if a paper's title or abstract contains malicious instructions.
- Ingestion points: Fetches content from arXiv, medRxiv, and bioRxiv as described in Phase 1 and Phase 3 of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize embedded instructions within the fetched preprint data.
- Capability inventory: The skill involves file writing (Phase 4: Export) and network access to search preprint servers.
- Sanitization: No sanitization or validation of the external content is specified before the agent processes and summarizes the data.
Audit Metadata