aif-build-automation
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes standard project analysis techniques (Glob, Grep, Read) to detect tech stacks. These tools are used solely to select the appropriate build automation template.
- [SAFE]: The generated build templates (Makefile, Taskfile, Justfile, Magefile) follow security best practices, including the use of strict shell flags (-euo pipefail) and avoiding hardcoded credentials.
- [SAFE]: The skill uses a restricted Bash environment (git commands only) and requires user confirmation for destructive actions (e.g., Justfile [confirm] attributes).
- [INDIRECT_PROMPT_INJECTION]: The skill ingests context from project-specific files (.ai-factory/DESCRIPTION.md). While this provides a surface for indirect instructions, it is a core feature for project-specific customization and is considered safe within the intended use case. Ingestion points: .ai-factory project metadata; Boundary markers: None; Capability inventory: Read, Write, Edit, Bash(git); Sanitization: None.
Audit Metadata