trello

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: All network requests target the official Trello API domain (api.trello.com). References to external documentation and setup pages also use trusted Atlassian/Trello domains.
  • [COMMAND_EXECUTION]: The skill utilizes curl and jq to interact with the Trello API. These are standard, well-known utilities and are used here for their intended purpose of making HTTP requests and processing JSON data.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes content (such as card names, descriptions, and comments) from an external source (Trello).
  • Ingestion points: External data is retrieved from api.trello.com via curl GET requests (SKILL.md).
  • Boundary markers: No explicit delimiters or instruction-bypass warnings are present in the command templates.
  • Capability inventory: The skill can create, update, and archive cards using curl POST and PUT requests (SKILL.md).
  • Sanitization: Retrieved content is structured by jq but no semantic sanitization or filtering is applied to prevent potential embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM