The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill configures a remote Model Context Protocol (MCP) server located at https://ask-samin-ochre.vercel.app/mcp. This server is hosted on Vercel and is owned by the skill vendor, ai-answer, as part of the intended functionality for knowledge retrieval.
[COMMAND_EXECUTION]: Instructions in SKILL.md and README.md provide shell commands (e.g., claude mcp add) for the agent or user to execute. These commands are used to register the remote MCP tools within the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it fetches external content from the Claude Club platform via search and fetch tools and interpolates that data into the prompt.
Ingestion points: Data retrieved via the search, fetch, and browse_curriculum tools defined in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the retrieved text.
Capability inventory: The skill utilizes search tools and environment configuration commands.
Sanitization: There is no evidence of content sanitization or validation for the data returned by the remote MCP tools.

Ask-Samin