skills/neekolas/claude-skills/babysit-pr/Socket

babysit-pr

Warn

Audited by Socket on Mar 18, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill’s capabilities align with PR babysitting, and its tool choices/data flows are mostly coherent and use official GitHub/Graphite paths. However, it is high risk because it gives an AI agent persistent autonomous authority to read untrusted PR content, modify code, push branches, and post public replies without per-action approval.

Confidence: 89%Severity: 78%

Audit Metadata

Analyzed At

Mar 18, 2026, 10:16 PM

Package URL

pkg:socket/skills-sh/neekolas%2Fclaude-skills%2Fbabysit-pr%2F@c7a4b4f08557d637e153798112681e40e6bbd465