aif-best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides static documentation and guidelines for clean code. No malicious patterns such as remote code execution, credentials exposure, or data exfiltration were found.
- [SAFE]: The skill incorporates project-specific context by reading .ai-factory/skill-context/aif-best-practices/SKILL.md and .ai-factory/ARCHITECTURE.md. This ingestion point allows the agent to tailor recommendations to the current codebase. While this pattern creates a surface for indirect instructions, it is assessed as safe because the behavior is integral to providing project-level context and is restricted to local file-reading tools. 1. Ingestion points: .ai-factory/skill-context/aif-best-practices/SKILL.md and .ai-factory/ARCHITECTURE.md. 2. Boundary markers: None specified. 3. Capability inventory: Read, Glob, Grep. 4. Sanitization: None.
Audit Metadata