tooluniverse-literature-deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations to non-whitelisted domains to retrieve scientific information. It uses tools like EuropePMC_search_articles, SemanticScholar_search_papers, and get_webpage_text_from_url to access data from academic repositories and journal publisher sites via DOI links.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from external literature sources.
- Ingestion points: Scientific abstracts and full-text snippets are ingested into the agent context in SKILL.md (Phase 2: Literature Search).
- Boundary markers: Absent. The instructions do not define the use of delimiters or specify that the agent should ignore instructions embedded within the retrieved literature.
- Capability inventory: The skill possesses file-writing capabilities (SKILL.md: [topic]_report.md, [topic]_bibliography.json) and wide network access through various integrated search tools.
- Sanitization: Absent. No validation or filtering of external content is specified before the synthesis of the research report.
Audit Metadata