macro-architecture

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill references a local Python script scripts/newadr.py used to automate the drafting of Architecture Decision Record (ADR) files. The script uses standard libraries and performs local file I/O within the project directory to scaffold documentation.
  • [INDIRECT_PROMPT_INJECTION]: The scripts/newadr.py script accepts user-provided input such as decision titles and status, which are then interpolated into a markdown template. This represents a potential surface for indirect injection; however, the impact is confined to the content of generated documents, and the script includes a slugify function to sanitize inputs used in filenames to prevent path traversal.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:50 PM