decision-records
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides structured guidance for documenting architectural decisions. The instructions do not attempt to override agent safety protocols or access sensitive system information. All external links point to the official documentation for the MADR standard.
- [COMMAND_EXECUTION]: The skill includes a utility script,
scripts/verify.sh, which is intended for the agent to run locally. This script performs linting on markdown files using standard Unix utilities (grep,awk,find,sort). The script is restricted to local file reading and pattern matching; it does not perform network operations, execute remote code, or modify system configurations.
Audit Metadata