ml-paper-writing
Fail
Audited by Socket on Mar 14, 2026
1 alert found:
MalwareMalwareSKILL.md
HIGHMalwareHIGH
SKILL.md
SUSPICIOUS: The core skill is coherent and mostly benign for academic writing, citation verification, and LaTeX workflows, with data flowing to expected official scholarly services. The main risk is the install guidance: it recommends an unnecessary, unpinned third-party `npx mcp-remote` bridge for Claude Code instead of Exa/Anthropic’s official native HTTP MCP path, creating medium supply-chain and transitive-trust risk without clear need.
Confidence: 89%Severity: 52%
Audit Metadata