adr
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill content is purely instructional, focusing on best practices and templates for technical documentation. It lacks any executable logic, system-level commands, or sensitive data access operations.
- [NO_CODE]: No scripts (Python, JavaScript, shell) are included in the skill. The functionality is delivered entirely through Markdown-based guidelines.
- [EXTERNAL_DOWNLOADS]: The skill references external resources including the official ADR website and the author's GitHub repository for examples. These are informational links for documentation purposes and do not involve the automated download or execution of remote code.
- [PROMPT_INJECTION]: The skill processes user-supplied architectural context to populate records. It utilizes a highly structured template with specific headers and blockquotes, which serve as boundary markers for external input and mitigate the risk of instruction override.
Audit Metadata