donedone

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package, which is the official command-line interface for the Membrane platform.
  • [COMMAND_EXECUTION]: Executes shell commands through the membrane CLI to manage connections, retrieve action schemas, and interact with the DoneDone API.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from the external DoneDone API.
  • Ingestion points: Data enters the agent's context through the output of commands like membrane action run and membrane request.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: The skill has broad capabilities to create, update, and delete various resources in DoneDone (tasks, projects, mailboxes).
  • Sanitization: There is no mention of sanitization or filtering of the content retrieved from external API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 06:41 PM