Research Ideation
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from research papers, creating a potential surface for indirect prompt injection.
- Ingestion points: External research paper content is retrieved using the
get_item_fulltexttool from the Zotero MCP server and web search results (referenced inSKILL.mdandreferences/zotero-integration-guide.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when processing external paper content.
- Capability inventory: The agent can write to local markdown files (e.g.,
literature-review.md,research-proposal.md) and perform library management tasks via the Zotero MCP server. - Sanitization: No explicit sanitization or filtering of the retrieved text is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill fetches research materials from trusted academic repositories.
- Evidence: Searches and downloads papers and metadata from well-known services such as arXiv and Google Scholar.
Audit Metadata