hunt-html-injection

Warn

Audited by Socket on Nov 12, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally coherent as a vulnerability-hunting guide, but it equips an AI agent with offensive web exploitation procedures, including exfiltration-oriented payloads and XSS escalation. There is no supply-chain or credential-harvesting installer behavior, so this is high-risk security tooling rather than confirmed malware.

Confidence: 90%Severity: 82%
Audit Metadata
Analyzed At
Nov 12, 2026, 05:48 PM
Package URL
pkg:socket/skills-sh/gsfsss%2Fclaude-bughunter%2Fhunt-html-injection%2F@33be843f668a7917203bb62357563ac13f75cb8d01021b915e2d7d7a4e85fcdc