architecture-decision-records

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions the installation of 'adr-tools' via Homebrew. This is a well-known open-source utility specifically designed for managing the ADR workflow described in the skill.
  • [COMMAND_EXECUTION]: Provides example shell commands for initializing and managing ADR directories using the 'adr-tools' CLI. These commands are standard for the tool's intended use and do not involve suspicious parameters or obfuscation.
  • [SAFE]: All external links target official documentation for well-known technology services (PostgreSQL, MySQL, MongoDB, PostGIS, KurrentDB) or established industry resources (Martin Fowler's blog). These references are used appropriately to provide context for the documentation templates.
  • [INDIRECT_PROMPT_INJECTION]: While the skill involves the agent generating file content based on user-provided architectural context (a data ingestion surface), this is the primary intended function of a documentation tool. The risk is minimal as the output consists of static documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 02:48 PM