Security audit

Gen Sage

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed security plugin that watches agent actions and scans installed plugins/skills; its higher-access behavior is purpose-aligned and user-configurable.

Install only if you want Sage to inspect agent commands, URLs, file operations, installed plugins, and skills. Review ~/.sage/config.json if you want to disable community telemetry, backend URL/file/package checks, or unknown skill uploads before use.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

VirusTotal

56/56 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution, suspicious.env_credential_access (+1 more)

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/index.cjs:14801
Evidence: function spawn(command, args, options) {

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: dist/mcp-server.cjs:16641
Evidence: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/index.cjs:4486
Evidence: const envDir = process.env.CLAUDE_CONFIG_DIR;

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/mcp-server.cjs:4540
Evidence: var debug = typeof process === "object" && process.env && process.env.NODE_DEBUG && /\bsemver\b/i.test(process.env.NODE_DEBUG) ? (...args) => console.error("SEM...

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/model-download-worker.cjs:1079
Evidence: bn = process.env.TESTING_TAR_FAKE_PLATFORM || process.platform;

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: dist/index.cjs.map:4
Evidence: "sourcesContent": ["import { randomBytes } from \"node:crypto\";\nimport * as fs from \"node:fs\";\nimport * as fsPromises from \"node:fs/promises\";\nimport { ...

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: dist/mcp-server.cjs.map:4
Evidence: "sourcesContent": ["import { randomBytes } from \"node:crypto\";\nimport * as fs from \"node:fs\";\nimport * as fsPromises from \"node:fs/promises\";\nimport { ...

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: dist/skill-upload-worker.cjs.map:4
Evidence: "sourcesContent": ["/**\n * Detached worker that uploads unknown skills to the Skill Analyzer and caches\n * the verdicts. Reads its work list from the pending ...