The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches data from the official Trello REST API (api.trello.com), which is a well-known service. This is the primary intended functionality of the skill.
[COMMAND_EXECUTION]: Utilizes standard CLI tools curl and jq to interact with the API and process JSON responses, which is consistent with the skill's stated purpose.
[DATA_EXFILTRATION]: Safely manages sensitive information by instructing users to use environment variables (TRELLO_API_KEY and TRELLO_TOKEN) for authentication instead of hardcoding secrets.
[PROMPT_INJECTION]: Potential surface for indirect prompt injection exists when the agent processes data from Trello (e.g., card descriptions or comments). Ingestion points: Trello API responses (SKILL.md). Boundary markers: Absent. Capability inventory: curl, jq. Sanitization: Absent. This risk is considered safe as it is inherent to the skill's core functionality.

trello