The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing and running the bgpt-mcp package from the npm registry using npx as an alternative setup method.
[REMOTE_CODE_EXECUTION]: Instructions provide a configuration for the agent to connect to a remote MCP server endpoint (https://bgpt.pro/mcp/sse), which executes logic on a remote server controlled by the vendor.
[COMMAND_EXECUTION]: Setup instructions include shell commands (npx) to configure the environment and run the BGPT tool.
[PROMPT_INJECTION]: The skill facilitates the ingestion of full-text data from scientific studies, creating a surface for indirect prompt injection attacks.
Ingestion points: Data retrieved from the search_papers tool (referenced in SKILL.md).
Boundary markers: Absent. The instructions do not specify the use of delimiters or markers to isolate retrieved paper content from the agent's core instructions.
Capability inventory: The skill allows access to the Bash tool (defined in SKILL.md frontmatter).
Sanitization: Absent. No logic or instruction is provided for sanitizing or validating the quantitative and qualitative data retrieved from external papers.

bgpt-paper-search