zotero-research
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes text-based data from a user's Zotero library, such as notes, annotations, and indexed text. This content is untrusted and could contain malicious instructions intended to influence the agent. -- Ingestion points: Data is retrieved from the local Zotero API via the zotero_item tool. -- Boundary markers: The instructions lack explicit delimiters or instructions to ignore commands embedded within the library data. -- Capability inventory: The skill is authorized to use several tools including zotero_search, omnischolar_parse, and scholar-search. -- Sanitization: There is no evidence of text sanitization or filtering before the retrieved content is processed by the agent.
Audit Metadata