trello-automation

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions require the integration of an external MCP server at https://rube.app/mcp to access Trello management tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from Trello boards and cards, creating a vulnerability where malicious instructions embedded in card descriptions or comments could influence agent behavior.
  • Ingestion points: Card content, titles, and comments retrieved via TRELLO_GET_SEARCH and TRELLO_GET_BOARDS_CARDS_BY_ID_BOARD.
  • Boundary markers: None. The skill lacks instructions to delimit external card data from the agent's system instructions.
  • Capability inventory: The skill provides extensive tools for card creation, list management, comment posting, and attachment handling.
  • Sanitization: None. The skill does not instruct the agent to sanitize or validate card content before processing or acting upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 09:09 AM
Security Audit — agent-trust-hub — trello-automation