skills/coinbase/cds/feature-planner/Gen Agent Trust Hub

feature-planner

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a clear separation between a non-technical discovery phase and a technical planning phase, which serves as a natural boundary for processing user-provided information.
  • [SAFE]: Tool usage is restricted and scoped to legitimate development tasks. It uses platform-provided tools for reading design context (Figma MCP) and creating project management tickets (Linear MCP).
  • [SAFE]: The instructions contain explicit guardrails against making assumptions and require a confirmation step ('Confirm understanding') before any technical planning or ticket creation occurs, mitigating risks associated with misinterpreting or directly passing through malicious user input.
  • [SAFE]: Use of the disable-model-invocation: true flag in the YAML frontmatter provides an additional layer of security by restricting the execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 10:17 PM