ai-rag

Enables the development of advanced retrieval-augmented generation systems with hybrid search and evaluation techniques.

Install this skill

94/100

Security score

The ai-rag skill was audited on Mar 8, 2026 and we found 6 security issues across 1 threat category. Review the findings below before installing.

low line 18

External URL reference

SourceSKILL.md

18	- Separate retrieval quality from answer quality; evaluate both (RAG: https://arxiv.org/abs/2005.11401).

low line 19

External URL reference

SourceSKILL.md

19	- Default to hybrid retrieval (sparse + dense) with reranking when precision matters (DPR: https://arxiv.org/abs/2004.04906).

low line 20

External URL reference

SourceSKILL.md

20	- Use a failure taxonomy to debug systematically (Seven Failure Points in RAG: https://arxiv.org/abs/2401.05856).

low line 23

External URL reference

SourceSKILL.md

23	- Threat-model RAG: retrieved text is untrusted input (OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/).

low line 68

External URL reference

SourceSKILL.md

68	- Trust boundaries: retrieved content is untrusted; apply the same rigor as user input (OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/).

low line 73

External URL reference

SourceSKILL.md

73	- Instrument each stage with tracing/metrics (OpenTelemetry GenAI semantic conventions: https://opentelemetry.io/docs/specs/semconv/gen-ai/).

Scanned on Mar 8, 2026

GitHub Stars 3

Rate this skill

Categorydata analytics

UpdatedApril 10, 2026