Railway

Black October Hype: Media Inflates AI Agent Role in PHP, GitLab and Cloud Platform Incidents

A detailed analysis reveals that recent high-profile cybersecurity stories have been sensationalized by attributing autonomous AI agent swarms to standard vulnerability disclosures and human-operated attacks. Critical PHP zero-day flaws enabling remote code execution were responsibly researched with GPT-5.6 Sol under OpenAI's Patch the Planet program, not by rogue AI bots launching millions of scans. The Argentina hospital compromises involved human operators using Anthropic's Claude Code CLI tool in a Human-in-the-Loop workflow rather than uncontrolled AI rebellion. Breaches at Zeabur, Railway and OpenCode stemmed from poor secret management and forgotten consoles, allowing credential theft for API abuse. A decade-old integer overflow in GitLab's Onigmo regex engine received a CVSS 10.0 score but had no connection to AI. The piece argues that adding AI narratives boosts clicks while obscuring classic attack patterns such as masscan-driven scanning after public PoC leaks.

Researcher Runs 100 Abliterated AI Agents Against His Own Accounts, Achieves Five Successful Breaches

A security researcher deployed roughly 100 autonomous AI agents based on abliterated open-source models to attempt unauthorized access to his online accounts over a five-hour period. The agents successfully compromised three accounts by exploiting vulnerabilities in legacy personal projects and two additional accounts through password reuse and credential stuffing. They also conducted 16 social engineering attempts, harvested and cross-verified personal data from public sources, and generated phishing pages targeting the researcher's Substack and Hacker News presence. Despite these successes, the agents failed to discover any zero-day vulnerabilities in third-party software or gain access to Tier-0 accounts such as Gmail, 1Password, or banking services. The experiment relied on abliterated versions of GLM-5.3 and DeepSeek V4 Flash models running on cloud GPUs, orchestrated via Codex CLI inside Docker containers with access to Railway infrastructure. Total compute cost reached approximately $210, equating to roughly $40 per successful account compromise. The researcher concluded that inexpensive swarms of such agents could soon enable low-skill attackers to systematically map and exploit an individual's entire online footprint.