asta
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a documentation layer for the Asta MCP server, teaching agents how to effectively query the Semantic Scholar database. It follows standard practices for tool-based skills without introducing executable code or malicious instructions.
- [EXTERNAL_DOWNLOADS]: The skill references an external endpoint at
https://asta-tools.allen.ai/mcp/v1and an API key registration form. Both resources are provided by the Allen Institute for AI (Ai2), a well-known research organization, and are required for the skill's intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external academic corpus (abstracts and snippets). While this creates a theoretical surface for indirect prompt injection, it is an inherent property of research tools, and the data originates from a curated academic source.
Audit Metadata