nozbe-teams

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Membrane CLI (@membranehq/cli) for all operations including authentication, action discovery, and API requests. These are controlled subprocess calls to a vendor-provided tool.
  • [PROMPT_INJECTION]: The skill processes data from Nozbe Teams, such as tasks and comments, which could contain malicious instructions designed to influence the agent's behavior (Indirect Prompt Injection).
  • Ingestion points: Data is retrieved via membrane action run and membrane request as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or protective headers when processing the external data.
  • Capability inventory: The skill executes commands through the membrane CLI to read and write data to the Nozbe Teams API.
  • Sanitization: No explicit sanitization or validation of the Nozbe Teams data content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:53 PM