The Agent Skills Directory

[SAFE]: The skill implements best practices for secret management by instructing users to store credentials in environment variables (TRELLO_API_KEY, TRELLO_TOKEN) rather than hardcoding them.
[SAFE]: All network requests are directed to the official Trello REST API (api.trello.com), which is a well-known and established service.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data by fetching card names, descriptions, and comments from Trello. This untrusted content is then presented to the agent, creating a potential surface for indirect prompt injection.
Ingestion points: Multiple curl commands in SKILL.md that retrieve card and board data.
Boundary markers: None defined in the skill instructions to separate Trello data from agent instructions.
Capability inventory: The skill uses curl for network operations and jq for JSON processing.
Sanitization: No explicit filtering or sanitization of the retrieved Trello content is performed by the provided shell commands.

trello