The Agent Skills Directory

[SAFE]: The skill manages authentication via environment variables ($OXINSIDER_API_KEY) and OAuth 2.1 with PKCE, explicitly advising against hardcoding credentials.
[SAFE]: All network operations and API endpoints target official vendor domains, specifically 0xinsider.com and api.0xinsider.com.
[SAFE]: External dependencies and installation commands refer to the official 0xinsider package on the NPM registry and the vendor's Homebrew tap.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external API data from api.0xinsider.com into the agent's context.
Ingestion points: API response data from endpoints such as /leaderboard, /platforms, and /usage (documented in SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat API data as untrusted content.
Capability inventory: The skill uses curl for data retrieval and interacts with a remote MCP server at https://0xinsider.com/mcp.
Sanitization: The skill recommends branching based on structured JSON error.code values but does not describe content sanitization for data interpolation.

0xinsider-api-access