Skills
Navigate
skills/tassiovale/claude-code-kit/bgpt-paper-search/Gen Agent Trust Hub

bgpt-paper-search

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of scientific paper content (methods, results, conclusions) extracted from full-text studies.
  • Ingestion points: Data enters the agent context via the search_papers MCP tool output.
  • Boundary markers: None specified in the instructions to delimit external content from system instructions.
  • Capability inventory: The agent is expected to interact with the MCP server via network requests to bgpt.pro.
  • Sanitization: No explicit sanitization or validation of the retrieved paper content is mentioned before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The documentation references external Node.js packages and remote services for initialization.
  • Dependencies: Mentions mcp-remote and bgpt-mcp for setup via npx.
  • Remote Service: Communicates with https://bgpt.pro/mcp/sse to perform searches.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:23 AM