deep-research

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions to use shell access for interacting with public scholarly APIs (Crossref, Semantic Scholar, arXiv, DBLP) to retrieve research data.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of information from external scholarly databases and general web search results.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection as the skill processes external literature and search metadata. Ingestion points: External API responses and web content (SKILL.md). Boundary markers: None identified. Capability inventory: Shell access and scholarly search tool usage (SKILL.md). Sanitization: The skill implements a rigorous citation verification protocol and multiple quality gates to ensure data integrity (references/citation-protocol.md, references/quality-gates.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 01:23 PM
Security Audit — agent-trust-hub — deep-research