Predictive Vulnerability Intelligence.

Product

  • Product
  • Pricing
  • Documentation

Company

  • About
  • Partnerships
  • Blog
  • Support

Legal

  • Terms
  • Privacy
  • Data Licensing

© 2026 FAUCET Technologies LLC. All rights reserved.

Agentfront

First CVE: Jan 14, 2026Active for: 1 yearTotal CVEs: 4

Agentfront's vulnerability footprint centers on a small ecosystem of agent-oriented and multi-channel connectivity products, including Enclave, FrontMCP adapters, and the FrontMCP SDK, which facilitate integration and automation across distributed systems. The observed weakness classes—code injection, infinite-loop conditions, protection-mechanism failures, and server-side request forgery—reflect the parser and execution-control demands of agent and adapter middleware handling untrusted input from multiple sources; current severity, exploitation, and exposure counts are shown alongside this summary.

FAUCET AI Generated
4
Total CVEs
More Total CVEs than 79% of tracked vendors
1.0
Avg CVEs / Product / Year
More Avg CVEs / Product / Year than 12% of tracked vendors
9.1
Avg CVSS Score
Higher Avg CVSS Score than 88% of tracked vendors
0.0%
In CISA KEV
Bottom 1%

Trends Over Time

The number and severity of CVEs published that impact products developed by Agentfront over time

Volume of CVEsAvg CVSS Base Score
First CVE
Jan 14, 2026
6 months ago
Most Recent CVE
Apr 8, 2026
107 days ago

Products(4 total)

Top CVEs

Signals from CVEs in this vendor scope (4 CVEs).

4 CVEs · Highest risk first

CVEPublishedCVSSRiskKEVExploit
CVE-2026-22686CRITICAL
Enclave is a secure JavaScript sandbox designed for safe AI agent code execution. Prior to 2.7.0, there is a critical sandbox escape vulnerability in enclave-vm that allows untrust
Jan 14, 202610.035NONO
CVE-2026-27597CRITICAL
Enclave is a secure JavaScript sandbox designed for safe AI agent code execution. Prior to version 2.11.1, it is possible to escape the security boundraries set by `@enclave-vm/cor
Feb 25, 202610.034NONO
CVE-2026-25533HIGH
Enclave is a secure JavaScript sandbox designed for safe AI agent code execution. Prior to 2.10.1, the existing layers of security in enclave-vm are insufficient: The AST sanitizat
Feb 6, 20268.827NONO
CVE-2026-39885HIGH
FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 2.3.0, the mcp-from-openapi library uses @apidevtools/json-schema-ref-parser to dereference
Apr 8, 20267.526NONO
View all 4 CVEs →

CVE Severity & Scoring

Severity distribution of CVEs that affect this vendor's products4 CVEs
50%
50%
Severity distribution among all CVEs352,231 CVEs
45%
40%
11%
HighCritical
Attack Vector
Local1 (25.0%)
Network3 (75.0%)
Unknown0 (0.0%)
Physical0 (0.0%)
Adjacent Network0 (0.0%)
Attack Complexity
Low4 (100.0%)
High0 (0.0%)
Unknown0 (0.0%)
User Interaction
None4 (100.0%)
Unknown0 (0.0%)
Required0 (0.0%)
Privileges Required
Low1 (25.0%)
High0 (0.0%)
None3 (75.0%)
Unknown0 (0.0%)

Exploit Exposure

Signals from CVEs in this vendor scope (4 CVEs).

CISA KEV
0 CVEs
0.0% of CVEs· Bottom 1%
Metasploit
0 CVEs
0.0% of CVEs· Bottom 1%
Nuclei
0 CVEs
0.0% of CVEs· Bottom 1%
ExploitDB
0 CVEs
0.0% of CVEs· Bottom 1%

Social Chatter

An overview of all social media posts that mention a CVE ID that affects a product developed by Agentfront.

Media Mentions

Media articles that mention a CVE ID that affects a product developed by Agentfront — matched by CVE ID, not by vendor name.

Top CNAs Publishing CVEs For Agentfront's Products

View all 1 CNAs →

Top CWEs