patsnap-patent-literature-search

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration references an official Docker image hosted on GitHub Container Registry (ghcr.io/patsnap/patent-literature-search-mcp). This is a legitimate distribution method for an MCP server from a professional service provider.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from 200M+ patents and scientific papers, which are external, untrusted sources.
  • Ingestion points: Intellectual property data, including titles, abstracts, and claims, are retrieved into the agent's context via the patsnap_search and patsnap_fetch tools.
  • Boundary markers: The provided documentation does not specify the use of delimiters or specific instruction-ignore markers for the retrieved content.
  • Capability inventory: The skill possesses network access to PatSnap's APIs and the capability to present large volumes of external text to the AI agent.
  • Sanitization: No explicit sanitization or filtering of the retrieved patent/literature content is described; original bibliographic and technical data is returned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — patsnap-patent-literature-search