The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (python3 scripts/status.py) to aggregate account status data. This is the primary function of the skill and is implemented using deterministic logic within the provided scripts.
[EXTERNAL_DOWNLOADS]: The mcp_client.py script communicates with https://mcp.prod.senpi.ai/mcp. This is the official API endpoint for the skill's vendor (senpi-ai) and is used to retrieve the user's account data (points, rank, loyalty) via the Model Context Protocol (MCP).
[CREDENTIALS_UNSAFE]: The skill requires a SENPI_AUTH_TOKEN environment variable. It follows safe security practices by reading this from the execution environment rather than hardcoding any secrets or tokens in the source code.
[DATA_EXFILTRATION]: While the skill accesses user account data (points, wallet addresses), this data is processed locally by the agent to display a status summary to the user. No evidence was found of data being sent to unauthorized third-party domains; all outbound requests are targeted at the vendor's production API.
[PROMPT_INJECTION]: The SKILL.md file contains instructions for the agent on how to format the output. These are standard behavioral guidelines and do not attempt to bypass safety filters or override system-level constraints.

senpi-account-status