The Agent Skills Directory

[SAFE]: The skill is designed for read-only access to public DefiLlama analytics via the uxc command-line tool.
[EXTERNAL_DOWNLOADS]: Fetches a curated OpenAPI schema from the vendor's official GitHub repository (github.com/holon-run/uxc). This is a legitimate configuration download from the skill author.
[COMMAND_EXECUTION]: Uses standard shell commands like command -v and uxc link to configure local CLI aliases. These are part of the intended setup workflow.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from api.llama.fi. However, the scope is restricted to read-only analytics, and the instructions include guardrails to parse specific JSON fields, minimizing the risk of processing malicious instructions embedded in API responses.
[DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations were detected. The network traffic is limited to the official api.llama.fi endpoint.

defillama-openapi-skill