websh
Warn
Audited by Socket on Jul 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
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