ClawHub
Back to skill

Security audit

Sefaria MCP Server

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Sefaria lookup MCP server with no evidence of hidden local access, persistence, credential handling, or destructive behavior.

Install it if you are comfortable running a Node MCP server that sends your text references and search queries to Sefaria's public API. For stricter supply-chain control, prefer installs that honor the lockfile or review dependency updates before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Unpinned Dependencies

Low
Category
Supply Chain
Content
"url": "git+https://github.com/abeperl/sefaria-mcp-server.git"
  },
  "dependencies": {
    "@modelcontextprotocol/sdk": "^1.29.0",
    "zod": "^4.4.3"
  },
  "devDependencies": {
Confidence
89% confidence
Finding
Using caret ranges for runtime dependencies allows future minor/patch releases to be installed automatically, which can introduce supply-chain risk if an upstream package is compromised or a breaking change slips through. In an MCP server context, runtime dependencies directly affect code executed by users, so version drift reduces build reproducibility and trust.

Unpinned Dependencies

Low
Category
Supply Chain
Content
},
  "dependencies": {
    "@modelcontextprotocol/sdk": "^1.29.0",
    "zod": "^4.4.3"
  },
  "devDependencies": {
    "@types/node": "^22.19.13",
Confidence
89% confidence
Finding
The zod dependency is specified with a caret range, permitting automatic adoption of newer compatible versions that may still introduce malicious or vulnerable code through the supply chain. While the immediate impact is limited, this weakens reproducibility and can expose consumers to upstream compromise without changes in this repository.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.