trello
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill guides the user to install the
@membranehq/clipackage from npm. This is the official command-line tool provided by the vendor (Membrane) for managing integrations. - [COMMAND_EXECUTION]: The skill utilizes several CLI commands (
membrane login,membrane connect,membrane action run,membrane action create) to interact with the Trello API. These commands are part of the platform's standard operational flow. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from Trello boards, such as card titles, descriptions, and comments, which could contain malicious instructions.
- Ingestion points: External data ingested via
membrane action runfrom Trello lists, cards, and comments. - Boundary markers: The instructions do not define specific delimiters or guardrails for the data returned from Trello actions.
- Capability inventory: The skill can list, create, and execute actions via the Membrane CLI.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the data fetched from Trello before use.
Audit Metadata