📰 Dev.to · Toni Antunovic

Sapphire Sleet (North Korean APT) compromised 140+ Mastra npm packages via postinstall hook to steal AI API keys and cloud credentials from developer machines.

AI coding tools trained on GitHub can suggest or hallucinate malicious packages from the 10,000+ trojan repos recently disclosed. Here is how the attack works a

The Miasma worm planted .claude/settings.json and .gemini/settings.json files in 73 Microsoft GitHub repositories to harvest cloud credentials the moment a deve

Pillar Security researchers chained a prompt injection in a public GitHub issue to a full supply chain compromise of the gemini-cli repository, earning a CVSS 1

A bootstrap API and a live feature-flag sync mean Anthropic can modify what Claude Code is told to do, at startup and every 60 seconds after, without shipping a

A new paper from arxiv shows LLM coding agents lose 30+ accuracy points as structural constraints accumulate, a phenomenon called constraint decay. Here is what

AI-generated PRs arrive 5x faster than human ones, but review speed has not changed. When reviewers are drowning in backlog, approval becomes a formality. Here

Configuration files can be exploited to inject persistent instructions via deeplinks and malicious PRs. Here is how to treat your agent config as the security b

Claude Code, Codex CLI, and Gemini-CLI share a TOCTOU trust model that lets a single malicious commit permanently own every future agent session. All three vend

Georgia Tech tracked 35 CVEs filed in March 2026, with 27 traced to Claude Code output. Here is what the data actually means for security teams and why volume a

Anthropic confirmed the MCP STDIO remote code execution vulnerability is by-design behavior. With 150 million downloads affected and no protocol fix coming, her

Today Socket Research Team published a report that needs to be in your queue: four SAP CAP npm...

AI coding agents invent package names that do not exist. Attackers register those exact names with malicious payloads. Here is how to validate every AI-generate

The TeamPCP group hijacked 75 tags of trivy-action on GitHub, turning every CI/CD pipeline that called Trivy into a silent credentials exfiltration machine. Her

The Axios supply chain attack exposed a critical gap: provenance attestations existed but a legacy token bypassed them entirely. Here is how to close that gap w

The axios npm supply chain attack of March 2026 deployed a RAT through AI coding agents autonomously running npm install. Learn how MCP connector poisoning work