trello

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to paste their Trello API key and token into the conversation and then directs running a command that embeds those values verbatim (ruby ... save_token.rb 'API_KEY' 'TOKEN'), which requires the LLM to receive and output secret values.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill fetches and displays user-generated Trello content from the Trello API (e.g., card descriptions in scripts/card.rb and comments in scripts/comments.rb, and the SKILL.md flow instructs presenting boards/lists/cards), so untrusted third‑party text can be read and could materially influence subsequent actions.