CVE-2026-44284Disclosure

LOWCVSS 6.3 · MEDIUM

Signal is active with 1 mentions in latest observed window

Immediate actions

Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.

Back to dashboard

0.0/ 10 priority

Sources & remediation

Other references

Weakness type (CWE)

CWE-918

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

STABLE

Threat summary

2 mentions across 2 observed days
Momentum state: stable

What's happening

Technical details provided in 2 signals
Disclosure: 2 classified signals
Peaked 1d ago at 1 mentions (2026-05-09); latest day: 1
2 total mentions across 2 days

Deep dive

Activity timeline2 mentions / 2d

Signal classification1 categories

Disclosure

2100.0%

Referenced assets1 URL

By indicator

https://www.cve.org/CVERecord?id=CVE-2026-44284

Full discourse2 posts

Cyera@cyera_io122d
Disclosure
The breakdown of the 6 CVEs discovered and responsibly disclosed by our team: • CVE-2026-44284 & 44285 (CRITICAL): Prototype pollution & RCE via schema loading/code generation • CVE-2026-44287, 44289, 44291 (HIGH): DoS & Prototype pollution during decoding • CVE-2026-44293 (MED): Unsafe descriptor handling
Post summary
The team has responsibly disclosed six new CVEs, detailing each vulnerability’s type and severity, including prototype pollution, RCE, DoS, and unsafe descriptor handling.
1000042
795 followersView on X
CVE@CVEnew152d
Disclosure
CVE-2026-44284 FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/r… https://www.cve.org/CVERecord?id=CVE-2026-44284
Post summary
CVE‑2026‑44284 reveals an SSRF flaw in FastGPT’s MCP tool URL handling before version 4.14.17; the post contains no PoC, exploit code, patch, or active exploitation evidence.
0000077
57.5K followersView on X

Explore more

Back to dashboard