autoresearch-agent

Warn

Audited by Socket on May 5, 2026

1 alert found:

Anomaly
AnomalyLOW
SKILL.md

SUSPICIOUS: the skill's core behavior is coherent with its stated purpose, but it grants an agent a high-autonomy edit/execute/git loop that can run indefinitely and use arbitrary evaluation commands. Install provenance is mostly consistent for the GitHub repo, with moderate extra risk from the unverified registry-based install path; no clear credential harvesting or malicious exfiltration is shown.

Confidence: 84%Severity: 58%
Audit Metadata
Analyzed At
May 5, 2026, 04:20 AM
Package URL
pkg:socket/skills-sh/alirezarezvani%2Fclaude-skills%2Fautoresearch-agent%2F@dc8f75dc3c972167f44e60f5d5834d9cf4950334