Skip to main content

autoresearch-loop

Applies Karpathy's autoresearch methodology to iteratively improve measurable artifacts like Claude skills and workflows.

Install this skill

or
25/100

Security score

The autoresearch-loop skill was audited on May 26, 2026 and we found 3 security issues across 1 threat category, including 3 critical. Review the findings below before installing.

Categories Tested

Security Issues

critical line 29

Eval function call - arbitrary code execution

SourceSKILL.md
29**The methodology is format-agnostic**: The loop works for any artifact type — code, prompts, documents, design systems, API configurations, process specs — as long as you can define an artifact, a me
critical line 116

Eval function call - arbitrary code execution

SourceSKILL.md
1166. **Regression suite**: When retiring old prompts, keep 1–2 of the most critical from each round in a small, persistent "regression suite" that runs alongside (not instead of) each new round's eval.
critical line 277

Eval function call - arbitrary code execution

SourceSKILL.md
277**Eval file management**: Over many rounds you'll accumulate eval_round1.md through eval_roundN.md plus regression_suite.md and holdout_eval.md. Operationally you need: the current round's eval (activ
Scanned on May 26, 2026
View Security Dashboard