write-tweet
Warn
Audited by Socket on Oct 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s purpose and most capabilities are coherent for tweet drafting, and the main API calls go to xAI’s official endpoint. However, core actions rely on opaque local executables (`./secretcurl`, `./notify`), and an API key is forwarded through an unverifiable wrapper, creating a high trust gap disproportionate to the provided transparency.
Confidence: 88%Severity: 82%
Audit Metadata