textme
Warn
Audited by Socket on Oct 1, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent about being a remote-control daemon for Claude, but its actual footprint is high risk by design: inbound messages from a whitelisted phone can drive filesystem operations, code execution, and approval flows on the host. Main concerns are the exposed remote execution surface, credential storage, SMS-based approval boundary, and installation from a personal GitHub repository rather than a stronger verified release channel. This is not confirmed malware, but it is a high-risk skill that should only be used with strong trust in the repo, a tightly scoped host, and a minimal whitelist.
Confidence: 87%Severity: 74%
Audit Metadata