trello-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server at
https://rube.app/mcpto retrieve tool schemas and execute Trello operations. - [PROMPT_INJECTION]: The skill processes external data from Trello (card names, descriptions, and comments), which creates a surface for indirect prompt injection if those fields contain malicious instructions intended for the AI agent.
- Ingestion points: Card details, search results, and board metadata retrieved from Trello APIs (SKILL.md).
- Boundary markers: No specific delimiters or warnings are provided to separate user-controlled Trello data from agent instructions.
- Capability inventory: The skill possesses capabilities to create, update, and manage Trello cards, lists, and boards.
- Sanitization: No explicit sanitization or validation of the content retrieved from Trello is described.
Audit Metadata