116 matches found
system_prompts_leaks
As seen in The Washington Post: See the hidden rules behind AI. Then use them to rewrite this article. May 11, 2026 System Prompts Leaks The purpose of this repo is to document the System Prompt instructions for all the AI chatbots out there - Claude, ChatGPT, Gemini etc. Recently Updated What|...
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...
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...
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...
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...
ANT-2026-GY2SF1XW · grok · Heap-buffer-overflow
heap-buffer-overflow high Severity Claude high · Security research firm high · Maintainer - Discovered by Claude Mythos Preview REPORT Anthropic's analysis, sealed at approval. Disclosure to the maintainer was performed by Ada Logics. ANT-2026-GY2SF1XW: Heap-buffer-overflow in...
Grok Build Uploaded Entire Git Repositories to xAI Storage, Not Just Files It Read
xAI's Grok Build coding CLI was uploading entire Git repositories, full commit history and all, to a Google Cloud Storage bucket run by xAI, not just the files a coding task needed. A researcher publishing as cereblab, testing version 0.2.93, captured one of those uploads, cloned the git bundle o...
Malicious code in ts-grok (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a981e7e3ba27d859a2c536cbc25c04ebece92e1992035226ea9246d8bd381f1d Package ts-grok ships a verbatim copy of big.js v7.0.1 same banner, author 'Michael Mclaughlin', repository URL https://github.com/MikeMcl/big.js.git...
MAL-2026-6321 Malicious code in ts-grok (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a981e7e3ba27d859a2c536cbc25c04ebece92e1992035226ea9246d8bd381f1d Package ts-grok ships a verbatim copy of big.js v7.0.1 same banner, author 'Michael Mclaughlin', repository URL https://github.com/MikeMcl/big.js.git...
Grok Is Still Hosting Sexualized Deepfakes of Famous Women
A WIRED investigation found dozens of “nudified” deepfake images and videos on Grok's website, including nonconsensual depictions of celebrities and at least one prominent US politician...
Researchers Show Copilot and Grok Can Be Abused as Malware C2 Proxies
Cybersecurity researchers have disclosed that artificial intelligence AI assistants that support web browsing or URL fetching capabilities can be turned into stealthy command-and-control C2 relays, a technique that could allow attackers to blend into legitimate enterprise communications and evade...
Grok continues producing sexualized images after promised fixes
Journalists decided to test whether the Grok chatbot still generates non‑consensual sexualized images, even after xAI, Elon Musk’s artificial intelligence company, and X, the social media platform formerly known as Twitter, promised tighter safeguards. Unsurprisingly, it does. After scrutiny from...
Elon Musk’s Grok ‘Undressing’ Problem Isn’t Fixed
X has placed more restrictions on Grok’s ability to generate explicit AI images, but tests show that the updates have created a patchwork of limitations that fail to fully address the issue...
Regulators around the world are scrutinizing Grok over sexual deepfakes
Grok’s failure to block sexualized images of minors has turned a single “isolated lapse” into a global regulatory stress test for xAI’s ambitions. The response from lawmakers and regulators suggests this will not be solved with a quick apology and a hotfix. Last week we reported on Grok's apology...
X Didn’t Fix Grok's ‘Undressing’ Problem. It Just Makes People Pay for It
X is allowing only “verified” users to create images with Grok. Experts say it represents the “monetization of abuse”—and anyone can still generate images on Grok’s app and website...
Grok Is Generating Sexual Content Far More Graphic Than What's on X
A WIRED review of outputs hosted on Grok’s official website shows it’s being used to create violent sexual images and videos, as well as content that includes apparent minors...
Grok Is Pushing AI ‘Undressing’ Mainstream
Paid tools that “strip” clothes from photos have been available on the darker corners of the internet for years. Elon Musk’s X is now removing barriers to entry—and making the results public...
Grok apologizes for creating image of young girls in “sexualized attire”
Another AI system designed to be powerful and engaging ends up illustrating how guardrails routinely fail when development speed and feature races outrun safety controls. In a post on X, AI chatbot Grok confirmed that it generated an image of young girls in “sexualized attire.” The potential...
Penetration Testing of Agentic AI: A Comparative Security Analysis across Models and Frameworks
Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple...