ai-context-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation providing guidance on context engineering, token budgeting, and history management. No executable scripts, command-line operations, or network requests are present.
- [INDIRECT_PROMPT_INJECTION]: The skill provides guidance on handling untrusted data (e.g., RAG chunks). It explicitly recommends security best practices, such as wrapping untrusted content in specific XML tags and instructing the model to ignore instructions within those blocks to prevent prompt injection attacks.
Audit Metadata