agent-reach
Warn
Audited by Socket on Aug 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s general purpose matches web/social/dev research, but its footprint is overly broad, relies on mutable same-org remote install docs, forwards users toward supplying cookies, and routes some reading through a third-party proxy. This looks more like a high-risk multi-tool aggregator than a tightly scoped reading/search skill.
Confidence: 85%Severity: 76%
Audit Metadata