craft-context-engineering

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown-formatted text providing instructions, guidelines, and examples for the CRAFT prompting framework. It does not contain any executable scripts (Python, JavaScript, etc.), binaries, or configuration files for automated execution.
  • [SAFE]: Comprehensive analysis of the instructional content and prompt examples reveals no malicious patterns. There are no attempts at prompt injection, data exfiltration, privilege escalation, or persistence. The provided URLs are static attribution links to well-known services (Notion) and the author's professional website, which do not pose a security threat in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 12:12 AM
Security Audit — agent-trust-hub — craft-context-engineering