trello

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows API calls that fetch Trello data (e.g., "List cards" and "List boards" curl examples to https://api.trello.com/1/... in SKILL.md), which pulls untrusted, user-generated content (card names, descriptions, comments) that the agent would read and could influence its subsequent actions.