330 casos · pág. 4/17
Researcher Harsh Jaiswal of Hacktron describes using the AI-assisted Hacktron CLI with a custom "JDBC driver pack" to audit decompiled JDBC drivers during a bug bounty event. The audit surfaced multiple vulnerabilities across vendor drivers, earning $85,000 in bounties. The headline finding is in the Databricks JDBC driver, where an attac…
Researcher Mohan Pedhapati of Hacktron ran an AI-driven audit against vinext, Cloudflare's Next.js reimplementation reportedly built in a week with AI assistance. The scan produced 45 findings, of which 24 were manually validated, including several Critical issues. The most serious bugs allow cross-user session data leakage, shared cache …
Researchers at Hacktron disclosed a vulnerability chain in Cluely, an Electron-based AI assistant that reads the user's screen and microphone. They found it in July 2025 and published in February 2026. The main window had no will-navigate handler, so a link in the AI's markdown response could navigate the whole app to an attacker-controll…
Researcher ahacker1, using the Hacktron AI tooling, disclosed a bypass of earlier fixes for prompt-injection-to-RCE in VS Code Copilot Chat agent mode. A TOCTOU flaw in the applyPatchTool component lets a crafted prompt write files outside the workspace without user confirmation. The attack can be triggered by pasting a prompt into Copilo…
Researchers at Hacktron disclosed a chain in Metabase Cloud that began with a bypass of the sanitization Metabase applies to H2 connection strings and ended in exposure of secrets belonging to other tenants. Metabase strips or rejects INIT= in the H2 URL, but the INIT value could be supplied in a separate details field that was never sani…
On July 25, 2026, Hacktron researchers chained a heap buffer overflow in libheif (reached through ImageMagick in Discourse's image-upload pipeline) with an OpenAI SSO weakness. This gave them RCE on the OpenAI community forum and takeover of ChatGPT/Codex accounts of forum users and OpenAI employees. To prove impact without reading sensit…
Hakai Security released Chupabase, a Python tool that finds and demonstrates insecure Supabase backend configurations in applications generated by the vibe coding platform Lovable. It parses the app's JavaScript bundles (and the sw.js Service Worker precache manifest) to recover the Supabase URL, the public anonKey and the API endpoint ma…
SmartLoader is a commodity loader in active deployment, attributed to Malware-as-a-Service infrastructure linked to LummaStealer delivery in recent campaigns. Reverse engineering shows it is built almost entirely from off-the-shelf parts: a stock signed LuaJIT 2.1.0-beta3 interpreter, a commercial Lua VM obfuscator from the game-cheat sce…
The Yokai research team at Hakai Security disclosed CVE-2026-40083, a SQL injection vulnerability in Cacti versions up to and including 1.2.30. An authenticated user with SNMP management (agent) permissions can run arbitrary SQL queries, reading or modifying the entire database. Exposed data includes bcrypt credential hashes, API tokens, …
A privilege escalation flaw, CVE-2026-16764 (GHSA-w2j3-x3j3-mm43, CVSS 3.1 7.8, CWE-269), affects OWASP DefectDojo. The REST API UserSerializer validates changes to issuperuser but not to isstaff. An authenticated user holding only the delegated auth.changeuser permission can therefore make themselves staff and then become superuser throu…
SafeDep analyzed sckit (the "supplychain.local worm"), a previously unreported cross-platform Go implant framework found on September 23, 2026 in the compromised MemTensor packages @memtensor/email protected (npm) and email protected (PyPI). It harvests credentials from developer machines and CI jobs, takes signed tasks from a C2 server, …
On September 23, 2026, an attacker published malicious versions of @memtensor/memos-cloud-openclaw-plugin (npm, versions 0.1.21, 0.1.23 and 0.1.25 per the article) and the MemoryOS Python library (PyPI, 2.0.34). Both carry the same Go implant, sckit, which harvests credentials from the home directory, exfiltrates them to servers under sky…
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
Trend Micro published its State of AI Security Report, 1H 2025, warning that AI infrastructure is being built from unsecured and unpatched components. The research found 200+ ChromaDB servers, 2,000 Redis servers and 10,000+ Ollama servers exposed to the internet with no authentication. It also reports zero-day vulnerabilities and exploit…
This F5 Labs explainer describes how quantum computing affects cryptography. Shor's algorithm can efficiently break the problems behind RSA, DSA, Diffie-Hellman and ECC, while Grover's algorithm only halves the effective strength of symmetric ciphers such as AES. The article stresses "harvest now, decrypt later" risk: an adversary who rec…
CVE-2026-9082 is a critical (CVSS 9.8) pre-authentication SQL injection in the JSON:API module of Drupal Core. It was published on May 20, 2026 and added to the CISA KEV catalog the same month, with a remediation deadline of May 27. F5 sensors recorded 576 exploitation attempts from 9 source IPs between May 20 and May 31, 2026. The earlie…
F5 Labs published its 2026 cybersecurity predictions and scored its 2025 forecasts at 6.5/8, by its own assessment. The 2025 review cites AI-powered botnets, attacks on AI model APIs, AI side-channel attacks on cryptography, APT use of hacktivist personas, and expanded Roskomnadzor powers to isolate or reroute Russian internet traffic fro…
F5 Labs, with Efflux sensor telemetry, profiled a persistent information-disclosure scanner operating from 78.153.140.203 in a netblock of AS202306 (HOSTGLOBAL.PLUS LTD), a UK ISP. The IP was first seen on 10 January 2025, vanished on 10 April, and returned on 11 July 2025. It scans 130 unique URLs: 80.23% are variations of /.env, 11.45% …
F5 Labs published its November 2025 AI Security Insights, drawn from the Comprehensive AI Security Index (CASI) and Agentic Resistance Scoring (ARS). Anthropic models took the whole top tier of the CASI leaderboard (Claude Haiku 4.5 at 95.89, Claude Sonnet 4.5 at 95.86, Claude Sonnet 4 at 95.33), while the GPT-5 family slipped, with GPT-5…
Proofpoint disclosed an active campaign, tracked as UNKCondorFiltration, that used the TeamFiltration offensive framework against more than 5,700 accounts across 28 Microsoft 365 tenants. It focused mainly on Chilean retail and financial institutions and originated from 1,487 unique AWS EC2 IP addresses. Seven accounts were compromised, a…
