blog
thoughts, updates, and insights from the superagent team.
When Terminal Output Owns Your Clipboard: OSC 52 in Warp
Affected Warp builds honored OSC 52 clipboard escape sequences from terminal output, allowing silent clipboard reads and writes with no default-deny gate.
▸read more
Frontier models miss 57% of threats in agent context
We ran 485 real artifacts through Claude 4.6 Opus with a security-focused system prompt. The model missed 57% of the threats brin had already identified. Here's the full breakdown.
▸read more
We Bypassed Grok Imagine's NSFW Filters With Artistic Framing
Text-to-image safety is broken. We generated explicit content of a real person using basic compositional tricks. Here's what we found, why it worked, and what this means for AI safety systems.
▸read more
The Threat Model for Coding Agents is Backwards
Most people think about AI security wrong. They imagine a user trying to jailbreak the model. With coding agents, the user is the victim, not the attacker.
▸read more
AI Is Getting Better at Everything—Including Being Exploited
As AI models become more capable and obedient, safety improvements struggle to keep pace. The GPT-5.1 safety score drop reveals a structural problem: capability and attack surface scale faster than safety.
▸read more
Are AI Models Getting Safer? A Data-Driven Look at GPT vs Claude Over Time
Are frontier models actually getting safer to deploy—or just smarter at getting around guardrails? We analyze 18 months of Lamb-Bench safety scores for GPT and Claude models.
▸read more
join our newsletter
updates on securing code and agents, vulnerability research, and product news.