AI coding agents leaked 13,000 internal company screenshots to public GitHub repos
When developers ask AI coding agents to prove that a user interface fix works, some agents have been posting the evidence where anyone can find it, according...
20 articles
When developers ask AI coding agents to prove that a user interface fix works, some agents have been posting the evidence where anyone can find it, according...
AI coding agents asked to share screenshots of code changes for review have put internal company images in public GitHub repositories, security company Glow ...
OpenAI has expanded its Codex platform with Codex Security Cloud, a cloud-hosted application security feature that continuously analyzes GitHub repositories,...
Security Affairs Malware newsletter includes a collection of the best articles and research on malware in the international landscape Malware Newsletter Thre...
Manifold Security found placeholder domains cited in 359,000 GitHub files and 349 AI agent skills serving cloaked scam…
Two third-party GitHub Actions previously compromised in a Mini Shai-Hulud campaign were re-enabled by their maintainer and remained accessible for more than...
The compromised GitHub Actions were originally disabled on May 18, 2026, after being found to execute malicious code that harvested sensitive credentials fro...
Two actions-cool GitHub Actions have been disabled for a second time after the repositories became accessible last week, months after they were compromised d...
GitHub allows organizations to install GitHub Apps that automate and extend certain functionality on the platform and have access to selected repositories an...
GitGuardian finds 474 leaked GitHub App keys still authenticating, including keys with admin access
Threat actors have compromised at least 65 public GitHub repositories in a software supply-chain campaign that abused npm trusted publishing to distribute a ...
The campaign, uncovered by LastPass and Delphos Labs, impersonates LastPass and at least 39 other companies.
An attacker copied about 170 of CrowdSec's private GitHub repositories on May 22 using the account of an employee who had just left, CrowdSec said on Septemb...
An ongoing malware campaign uses SEO-optimized GitHub repositories to impersonate well-known software firms to push a previously undocumented information ste...
A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even ...
Four major AI coding agents, Claude Code, Codex, GitHub Copilot and Gemini CLI, all share the same zero-click RCE vulnerability, one that could give an attac...
Hardcoded API keys, access tokens and other credentials used by AI coding tools have been found in publicly accessible MCP configuration files on GitHub, acc...
OpenAI published a framework for disclosing model misalignment alongside six reports describing problematic behavior. The post OpenAI Says Its Models Searche...
Kaspersky GERT experts have uncovered a new campaign by the NightEagle APT, featuring the GhostContainer backdoor and tools hosted on GitHub. The group is al...
Two critical ArangoDB vulnerabilities can allow unauthenticated attackers to access protected database APIs and, after obtaining valid database access, escal...