Skip to content

VSRVibe Security Radar

Findings Trends How we verify

Loading case details…

Vibe Security Radar

A mechanism-level study of vulnerabilities contributed by AI-written code. Each finding connects an advisory to the relevant change, residual vulnerability, and security fix.

Sources: first-party security advisories · public Git history · release artifacts

Data through Sep 26, 2026

By AI tool

Claude
GitHub Copilot
Cursor
ChatGPT/Codex

By root cause

Authentication & access control
Injection & unsafe execution
SSRF & network boundaries
Path & link handling
Validation & fail-open logic
Resource abuse & availability

Project

GitHub Data (CSV)Atom feed Contact

Findings

Published vulnerabilities where an AI-assisted change introduced the flaw, exposed the vulnerable path, or left a security fix incomplete. Open a finding to see its evidence, caveats, contributing change, and fix status.

AI tool

AI contribution

Severity

Root cause

Language

Search/

AI toolAI contributionSeverityRoot causeLanguage

284 findings

RepositoryAdvisory monthCSVSort

Nodemailer's address parser appends each address part to one growing string. A Claude-co-authored change in 9.1.0 reads that string's last character before every append, which V8 can turn into a copy of the whole string, so comment-separated addresses parse in quadratic time. Mailparser feeds inbound headers here. Release 10.0.5 caches the last character.
HighCVE-2026-90776Sep 11, 2026nodemailer/nodemailerTypeScriptClaudeDirect introductionResource abuse & availability
When Nodemailer's address parser cannot read an address strictly, it scans the free text. A Claude-co-authored repair in 10.0.6 replaced the slow regular expression with a scanner whose two new probes still searched the rest of the value, so long headers could stall the event loop until 10.0.9 bounded them. Found by source analysis, not timing.
HighGHSA-V53P-9FQP-M79JSep 11, 2026nodemailer/nodemailerTypeScriptClaudeIncomplete remediationResource abuse & availability
Claude-assisted browser gateway used an unanchored pattern to validate Chrome extension origins, so a crafted page could open the debugging WebSocket from any domain.
CVE-2026-55536Aug 25, 2026mervinpraison/praisonaiPythonClaudeDirect introductionAuthentication & access control
AI-assisted scope hardening on the user-list route left ordinary sessions exempt from capability checks and relied on an administrator check that the existing service did not perform. The exposure predated that hardening. Other dashboard routes and the separate WebSocket log path also lack required role authorization, but those independent omissions are not attributed to this change. Version 4.5.1 adds an administrator check for user listing only. Dashboard and log-stream exposure remains in the inspected source revision; no complete advisory repair or binary equivalence is established.
CVE-2026-79665Aug 25, 2026lin-snow/ech0GoCursorFlawed AI-written codeAuthentication & access control
PraisonAI added an agent-invocation route without enforcing the configured API key. The repair installs shared authentication middleware on the application.
HighCVE-2026-55538Aug 25, 2026mervinpraison/praisonaiPythonUnidentified AI toolFlawed AI-written codeAuthentication & access control
PraisonAI checked literal IP addresses without resolving ordinary hostnames before Spider requests. The repair checks DNS results for blocked addresses and rejects resolution failures.
HighCVE-2026-55526Aug 25, 2026mervinpraison/praisonaiPythonClaudeDirect introductionSSRF & network boundaries
Hardening of the FrameNet corpus reader tightened the checks on the names that are interpolated into XML file paths, but a corpus subdirectory can hold a symlink whose name passes those checks and points outside the corpus root, so the reader returns text from a file outside the corpus.
CVE-2026-62384Aug 22, 2026nltk/nltkPythonClaudeFlawed AI-written codePath & link handling
A CLI coding assistant co-authored the commit that added the transaction API, and its single-transaction endpoint fetched any record by primary key without company scoping or a permission check.
CVE-2026-77759Aug 21, 2026roskus/prospero-flow-crmPHPClaudeDirect introductionAuthentication & access control
AI-written code exposed a Management API that fail-open authenticated an empty token and passed user input to shell exec, enabling remote OS command injection.
MediumCVE-2026-76761Aug 20, 2026chenhg5/cc-connectGoClaudeNew attack surfaceInjection & unsafe execution
AI-written webhook code treated an empty configured token as authenticated, then passed a caller-supplied command to a shell, enabling unauthenticated remote code execution.
MediumCVE-2026-76760Aug 20, 2026chenhg5/cc-connectGoClaudeDirect introductionInjection & unsafe execution
An AI-assisted webhook request/test component adds response readback to an earlier outbound-request primitive. The shipped SQL-backed test path can cross the intended destination boundary when an admitted client can configure and test webhooks.
CriticalCVE-2026-64849Aug 17, 2026mlflow/mlflowPythonClaudeFlawed AI-written codeSSRF & network boundaries
The AI-written code loads the first .so file matching a broad glob pattern without verifying integrity, enabling arbitrary code execution via a malicious module.
CriticalCVE-2026-74872Aug 17, 2026jahlives/openssl_encryptPythonClaudeDirect introductionOther or unclear
AI-written code interpolated a caller-controlled username into a shell command executed via execAsync, allowing command substitution and arbitrary OS command execution as the server user.
CVE-2026-55157Aug 14, 2026ooples/token-optimizer-mcpJavaScriptClaudeDirect introductionInjection & unsafe execution
AI-written web server code exposed session log endpoints without authentication, letting unauthenticated users read files via path traversal.
MediumCVE-2026-55156Aug 14, 2026ooples/token-optimizer-mcpJavaScriptClaudeDirect introductionPath & link handling
The AI-assisted change that added the MCP server also added a markdown renderer for report text, and its link conversion writes the URL into an href attribute without escaping quotes, so a stored link can run script when a report is opened.
CVE-2026-19744Aug 13, 2026ccyl13/pentestifyPythonClaudeDirect introductionInjection & unsafe execution
An AI-assisted dictionary-redaction repair left deeply nested JSON lists behind the recursion cutoff, allowing sensitive-key values to appear unmasked in authorized Variable responses and the UI.
MediumCVE-2026-54183Aug 12, 2026apache/airflowPythonClaudeIncomplete remediationPath & link handling
A CLI coding assistant co-authored the commit that added the in-process TURN relay server, and its UDP receive loop was started fire and forget with the only exception handler outside the loop.
GHSA-PFVM-W89X-94JWAug 12, 2026sipsorcery-org/sipsorceryC#ClaudeDirect introductionOther or unclear
A coding assistant co-authored the commit that added follows and notifications to this Python web app, and the four new endpoints that change that state were exposed as plain GET routes, so any page could trigger them for a signed-in user.
CVE-2026-73162Aug 11, 2026misp/cti-transmutePythonClaudeDirect introductionAuthentication & access control
With the optional DeepStream stack installed, request-level video settings can activate GPU decoding without startup authorization and omit the normal metadata pixel check.
CVE-2026-78684Aug 11, 2026vllm-project/vllmPythonClaudeDirect introductionAuthentication & access control
A coding assistant co-authored the commit that added emoji reactions to the comment system of this Python web app, and the new reaction endpoint never checked whether the caller was allowed to see the comment it changed.
CVE-2026-73155Aug 11, 2026misp/cti-transmutePythonClaudeDirect introductionAuthentication & access control

Page 1 of 15

Page 1 of 15
…