build-rag-search-stacks

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable scripts or active code. It functions as an orchestration layer using Markdown to guide an agent through architectural decision-making for search systems.
  • [EXTERNAL_DOWNLOADS]: The skill references the author's own GitHub repositories (hiteshbandhu/ingest-into-skills and hiteshbandhu/skills-i-use) and a YouTube playlist for supplementary learning notes and source material. These references are static links for the user/agent to read and do not involve automated script execution or suspicious data retrieval.
  • [PROMPT_INJECTION]: The instructions are clear and instructional without any attempts to bypass safety filters or override system prompts. Benign instructional phrases like 'Stop summarizing' are used to maintain task focus.
  • [DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file path access, or network exfiltration patterns was found. The skill suggests an output directory for saving user-requested artifacts (diagrams and checklists), which is a standard functional behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 05:38 AM
Security Audit — agent-trust-hub — build-rag-search-stacks