trello

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI tool globally via npm (@membranehq/cli). This is a legitimate dependency provided by the skill's author to facilitate interaction with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill uses various membrane CLI commands to perform authentication, discover actions, and execute API requests. These commands are necessary for the skill's intended functionality to interact with the Trello API.
  • [PROMPT_INJECTION]: While no direct malicious injections were found, the skill is designed to ingest data from Trello (boards, lists, and cards). This introduces a surface for indirect prompt injection if the agent processes untrusted content from shared project management environments without proper sanitization.
  • Ingestion points: Trello boards, lists, cards, and comments accessed via membrane action run or membrane request.
  • Boundary markers: None explicitly mentioned in the skill instructions.
  • Capability inventory: The skill can perform network requests, list connections, and execute actions that modify Trello data.
  • Sanitization: No explicit sanitization or validation of the ingested Trello data is described in the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 02:37 AM