sequential-thinking

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a documentation and configuration package for the Sequential Thinking MCP tool. It enables structured reasoning and problem decomposition through iterative steps.
  • [EXTERNAL_DOWNLOADS]: The installation instructions reference the @modelcontextprotocol/server-sequential-thinking package via NPX. This is an official component of the Model Context Protocol ecosystem and is considered a well-known and trusted source.
  • [COMMAND_EXECUTION]: The skill documentation provides examples of how the agent should call the mcp__reasoning__sequentialthinking tool. These calls are restricted to the intended reasoning parameters (thought content, step numbers, and branching identifiers) and do not involve arbitrary shell command execution.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or suspicious network operations were identified. The tool operates on the agent's internal reasoning context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:15 PM
Security Audit — agent-trust-hub — sequential-thinking