architecture-decision-records

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily instructional and documentation-oriented, providing templates and best practices for architectural decision-making. It follows the principle of least privilege by restricting its own execution environment to the 'Read' tool.
  • [EXTERNAL_DOWNLOADS]: External references are limited to reputable technical documentation and community-standard open-source projects (e.g., adr.github.io, npryce/adr-tools, and PostgreSQL official documentation). These links are provided for developer reference and do not involve any automated or unsafe data fetching.
  • [COMMAND_EXECUTION]: The skill documentation describes standard command-line operations for ADR management, such as using the adr-tools CLI and basic file manipulation (cp). These are presented as manual steps within a developer's workflow and are not configured for silent or autonomous execution by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:53 PM
Security Audit — agent-trust-hub — architecture-decision-records