websh

Warn

Audited by Socket on Jul 22, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill’s stated purpose matches web navigation and local caching, and it has no obvious supply-chain or credential-forwarding behavior. However, it gives an AI agent autonomous browsing and eager crawling of arbitrary untrusted web content while also allowing local file writes and background execution, creating a significant indirect prompt-injection and autonomy risk disproportionate to a simple browsing helper.

Confidence: 91%Severity: 74%
Audit Metadata
Analyzed At
Jul 22, 2026, 12:46 AM
Package URL
pkg:socket/skills-sh/MaxMiksa%2FAuto-Company%2Fwebsh%2F@9a0780b6bdf4ce399402430f9e0bc1637f2848c49b840772c7168952afb702df
Security Audit — socket — websh