architecture-decision-records
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is to provide architectural documentation templates and best practices. It contains no executable code or malicious instructions.
- [EXTERNAL_DOWNLOADS]: Recommends the installation of
adr-toolsvia Homebrew, a well-known package manager. This is a legitimate dependency for the stated purpose and points to a well-known community repository on GitHub. - [COMMAND_EXECUTION]: Contains example shell commands for the
adr-toolsutility (e.g.,adr init,adr new). These are intended for user-controlled execution to initialize and manage ADR files and do not include automated or silent execution patterns. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing and maintaining markdown files (ADRs) within a project's documentation directory. While the agent processes these external files, the risk of injection is mitigated by the structured nature of the templates and the fact that the skill focuses on generating new content based on user input.
Audit Metadata