Lucene search
+L

266 matches found

Kitploit
Kitploit
•added 2026/11/13 7:44 a.m.•68 views

system_prompts_leaks

System Prompts Leaks Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode,...

6.2AI score
SaveExploits0References22
Kitploit
Kitploit
•added 2026/11/10 2:49 a.m.•36 views

Grok-backdoor

Grok-backdoor Grok-backdoor is a simple python based backdoor, it uses Ngrok tunnel for the C&C communication. Ngrok-backdoor can generate Windows, Linux and Mac binaries using Pyinstaller. How it works: Ngrok exposes local servers behind NATs and firewalls to the public internet over a secure...

6.2AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
•added 2026/10/27 1:29 p.m.•12 views

UK Politician Jess Asato Got Deepfaked. Now She’s Taking xAI to Court

Jess Asato’s public campaigning for victims of online abuse put her in the crosshairs of Grok’s deepfake scandal. Then the UK member of parliament became a victim of the abuse herself...

6AI score
SaveExploits0
OPENSUSE Linux
OPENSUSE Linux
•added 2026/10/27 12:00 a.m.•18 views

grok-build-1.0.45+git20260929.2bdd1d6-2.1 on GA media (moderate)

grok-build-1.0.45+git20260929.2bdd1d6-2.1 on GA media Announcement ID: openSUSE-SU-2026:12141-1 Rating: moderate Cross-References: CVE-2026-109349 CVE-2026-109350 CVE-2026-109351 CVSS scores: CVE-2026-109349 SUSE : 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H CVE-2026-109349 SUSE : 8.7...

8.7CVSS6.1AI score0.00322EPSS
SaveExploits0
Tenable Nessus
Tenable Nessus
•added 2026/10/22 12:00 a.m.•36 views

openSUSE 16: grok-build / grok-build-bash-completion / etc (openSUSE-SU-2026:22130-1)

"The remote openSUSE 16 host has packages installed that are affected by multiple vulnerabilities as referenced in the openSUSE-SU-2026:22130-1 advisory. Changes in grok-build: - CVE-2026-109349: gix-pack pack version 3 header assertion failure boo1285155 - CVE-2026-109350: gix-pack ofs-delta...

7.1CVSS6.1AI score0.00322EPSS
SaveExploits0References7
OPENSUSE Linux
OPENSUSE Linux
•added 2026/10/20 12:00 a.m.•47 views

Security update for grok-build (important)

openSUSE security update: security update for grok-build ------------------------------------------------------------- Announcement ID: openSUSE-SU-2026:22130-1 Rating: important References: bsc1285155 Cross-References: CVE-2026-109349 CVE-2026-109350 CVE-2026-109351 CVSS scores: CVE-2026-109349...

8.7CVSS6AI score0.00322EPSS
SaveExploits0References1
osv_opensuse
osv_opensuse
•added 2026/10/19 4:28 p.m.•31 views

OPENSUSE-SU-2026:22130-1 Security update for grok-build

This update for grok-build fixes the following issues: Changes in grok-build: - CVE-2026-109349: gix-pack pack version 3 header assertion failure boo1285155 - CVE-2026-109350: gix-pack ofs-delta base-distance handling flaw boo1285155 - CVE-2026-109351: gix-pack header object-count denial of servi...

7.1CVSS6AI score0.00322EPSS
SaveExploits0References4
osv_opensuse
osv_opensuse
•added 2026/10/15 12:00 a.m.•45 views

OPENSUSE-SU-2026:12141-1 grok-build-1.0.45+git20260929.2bdd1d6-2.1 on GA media

These are all security issues fixed in the grok-build-1.0.45+git20260929.2bdd1d6-2.1 package on the GA media of openSUSE Tumbleweed...

7.1CVSS6AI score0.00322EPSS
SaveExploits0References3
The Hacker News
The Hacker News
•added 2026/10/08 2:12 p.m.•40 views

ARTEX AI Pentesting Tool Used in Data Theft Attacks on South Korean Financial Firms

Cybersecurity researchers have disclosed details of a targeted campaign aimed at South Korean financial organizations that used an artificial intelligence AI pen testing tool named ARTEX to carry out the attacks. The activity, per CrowdStrike Intelligence, was active from late September to early...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/24 12:00 a.m.•55 views

LLM Agents Can Easily Tamper with Their Own Traces

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Cod...

5.9AI score
SaveExploits0
OSS-Fuzz
OSS-Fuzz
•added 2026/09/13 5:35 p.m.•46 views

grok:grk_decompress_fuzzer: Heap-buffer-overflow in grk::PacketIter::init

Project: https://github.com/GrokImageCompression/grok.git https://github.com/GrokImageCompression/grok-test-data.git Detailed Report: https://oss-fuzz.com/testcase?key=6331592625422336 Project: grok Fuzzing Engine: honggfuzz Fuzz Target: grkdecompressfuzzer Job Type: honggfuzzasangrok Platform Id...

5.7AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
•added 2026/09/03 9:56 p.m.•90 views

Nobody Is Saying Why OpenAI and Anthropic Had Outages Today

ChatGPT, Claude, and Grok all suffered outages at nearly the exact same time for reasons that remain murky...

5.9AI score
SaveExploits0
OSS-Fuzz
OSS-Fuzz
•added 2026/09/03 8:44 p.m.•25 views

grok:grk_decompress_mercury_fuzzer: Use-of-uninitialized-value in bool grk::WaveletReverse::partial_tile<int, int, 1u, 4u, grk::Partial53<int, int

Project: https://github.com/GrokImageCompression/grok.git https://github.com/GrokImageCompression/grok-test-data.git Detailed Report: https://oss-fuzz.com/testcase?key=5849385926459392 Project: grok Fuzzing Engine: libFuzzer Fuzz Target: grkdecompressmercuryfuzzer Job Type: libfuzzermsangrok...

5.8AI score
SaveExploits0
Malwarebytes
Malwarebytes
•added 2026/08/25 11:34 a.m.•50 views

Grok fooled into stealing user chat, location data, and more

A new type of prompt injection attack shows why giving AI assistants access to browsers, code tools, and private data deserves extra caution. AI researchers describe "Cryptographic Context Injection"—an attack that hides malicious instructions inside encrypted data. The AI is then persuaded to...

5.8AI score
SaveExploits0
OSS-Fuzz
OSS-Fuzz
•added 2026/08/22 10:26 a.m.•30 views

grok:grk_decompress_fuzzer: Use-of-uninitialized-value in grk::TileCodingParams::readMct

Project: https://github.com/GrokImageCompression/grok.git https://github.com/GrokImageCompression/grok-test-data.git Detailed Report: https://oss-fuzz.com/testcase?key=5027344826564608 Project: grok Fuzzing Engine: libFuzzer Fuzz Target: grkdecompressfuzzer Job Type: libfuzzermsangrok Platform Id...

5.4AI score
SaveExploits0
OSS-Fuzz
OSS-Fuzz
•added 2026/08/21 10:19 a.m.•23 views

grok:grk_decompress_mercury_fuzzer: Heap-buffer-overflow in bool grk::GrkImage::compositePlanar<int>

Project: https://github.com/GrokImageCompression/grok.git https://github.com/GrokImageCompression/grok-test-data.git Detailed Report: https://oss-fuzz.com/testcase?key=6270477761576960 Project: grok Fuzzing Engine: libFuzzer Fuzz Target: grkdecompressmercuryfuzzer Job Type: libfuzzerasangrok...

5.4AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/08/20 2:36 p.m.•109 views

New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data

Adversa AI has disclosed an attack technique that it says can cause xAI's Grok chatbot to send a user's name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page. The AI...

6.5AI score
SaveExploits0
Github Security Blog
Github Security Blog
•added 2026/08/19 7:15 p.m.•39 views

grok-faf-mcp has an arbitrary local file read via unconfined `path` argument in FAF tools

Summary Several grok-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...

5.4AI score
SaveExploits0References3Affected Software1
Patchstack
Patchstack
•added 2026/08/19 7:15 p.m.•34 views

NPM: grok-faf-mcp has an arbitrary local file read via unconfined `path` argument in FAF tools

NPM: grok-faf-mcp has an arbitrary local file read via unconfined path argument in FAF tools vulnerability discovered by ? in WordPress Npm grok-faf-mcp versions = 1.5.2...

5.4AI score
SaveExploits0References3Affected Software1
osv_ghsa
osv_ghsa
•added 2026/08/19 7:15 p.m.•32 views

GHSA-CC2G-GQ8C-R332 grok-faf-mcp has an arbitrary local file read via unconfined `path` argument in FAF tools

Summary Several grok-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...

7.5CVSS5.4AI score
SaveExploits0References3
Rows per page
Query Builder