blog
thoughts, updates, and insights from the superagent team.
The OpenAI / Hugging Face incident and the case for autonomous security
OpenAI evaluation agents reached Hugging Face through a chain of familiar software and access-control failures. The incident shows why security has to connect detection, investigation, and repair.
▸read more
When a Trusted Contributor Gets Compromised
We analyzed 8,897 evidence-backed GitHub posture findings to measure how repository controls limit a compromised contributor.
▸read more
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
join our newsletter
updates on securing code and agents, vulnerability research, and product news.