bgpt-paper-search
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include the use of
npx mcp-remoteandnpx bgpt-mcp. These commands download and execute packages directly from the npm registry at runtime. - [COMMAND_EXECUTION]: The skill identifies
Bashas an allowed tool to facilitate the execution of npm commands for setup and server interaction. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from an external scientific database.
- Ingestion points: The
search_paperstool retrieves experimental data, methods, and conclusions from the remote endpoint athttps://bgpt.pro/mcp/sse. - Boundary markers: There are no specified delimiters or instructions to treat the retrieved content as untrusted data.
- Capability inventory: The skill environment allows the use of
Bash, which could be targeted by instructions embedded in the paper data. - Sanitization: The instructions do not describe any validation or sanitization of the remote paper data before it is presented to the agent.
Audit Metadata