trello-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect prompt injection surface detected. The skill retrieves data from Trello cards and boards, which may contain instructions from untrusted external contributors that could influence agent behavior.
- Ingestion points:
TRELLO_GET_SEARCHandTRELLO_GET_BOARDS_CARDS_BY_ID_BOARDin SKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters for external data.
- Capability inventory: Card creation, member assignment, and board management tools.
- Sanitization: Absent; the skill does not suggest filtering or escaping retrieved content before processing.
- [EXTERNAL_DOWNLOADS] (LOW): The skill references an external MCP server endpoint (
https://rube.app/mcp) for functionality. While this is the intended setup for the Rube integration, the domain is not on the predefined trusted list.
Audit Metadata