leetcode-problem-fetcher

Warn

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation instructs users to install an external Model Context Protocol (MCP) server using the command npx -y @jinzcdev/leetcode-mcp-server. This command downloads and executes code from a third-party package hosted on npm that is not associated with a verified or trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external problem descriptions and metadata fetched from the LeetCode API, which serves as an ingestion point for untrusted data. This content could theoretically contain instructions designed to manipulate the agent's behavior.
  • Ingestion points: Problem data retrieved from leetcode.com/graphql via the get_problem and search_problems tools.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands in the fetched data.
  • Capability inventory: The skill uses WebFetch to access the API and Bash to execute the MCP server commands.
  • Sanitization: There is no evidence of sanitization or strict schema validation for the Markdown content fetched from LeetCode.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from leetcode.com. While LeetCode is a well-known platform, the automated retrieval of content without integrity checks on the client side is noted.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 08:23 PM