autoresearch
What this skill does
Autonomous iterative experimentation loop for programming tasks, inspired by Karpathy's autoresearch. Used for autonomous improvement, iterative optimization, experiment loops, performance tuning, and
github/github - Tool Misuse - 37k stars
Threat analysis
Skill info
pkg:github/github/awesome-copilot@dae77f2?skill=autoresearchAssessments (1)
Tool Misuse
Tool Misuse via local-llm-review
SKILL.md
The skill requires terminal access and git, and it commits every experiment attempt. If not properly constrained, this could lead to unintended code changes, data loss, or unauthorized commits to a reBadge
Add the Anomity scan badge for autoresearch to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of autoresearch? Report an issue or request a rescan.
