principle-foundational-thinking
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill exclusively contains architectural guidelines and engineering principles. All instructions are benign and focused on best practices for software development.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local reference file (
../saltmode/references/host-adapter.md). While this represents a data ingestion surface, it targets a local documentation file within the expected environment and does not involve untrusted external data or dangerous capabilities. - [NO_CODE]: The skill consists only of documentation and configuration files without any executable scripts or command execution patterns.
Audit Metadata