agent-reach
Warn
Audited by Socket on Oct 12, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill's high-level purpose is coherent, but its actual footprint relies on multiple unrelated third-party CLIs, forwards credentials to unofficial tooling, and uses intermediary readers/proxies to bypass official API paths. This looks more like a risky aggregation stack than outright malware, with supply-chain and credential-forwarding concerns as the main issues.
Confidence: 87%Severity: 79%
Audit Metadata