blog
thoughts, updates, and insights from the superagent team.
Introducing DFIP: Faster inference for decision models
PPLX-Decider went from 74.54 ms to 30.14 ms on short yes/no requests. DFIP studies how to reduce decision model latency and where the gains hold up.
▸read more
Introducing Security-One 27B
A 27B decision model for always-on security triage across applications, agents, code, and infrastructure. Available through our API or open weights.
▸read more
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
Building a Security Factory with Superagent and Cursor
Superagent acts as the attacker and Cursor as the executor, turning verified findings into reviewed pull requests in minutes.
▸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
join our newsletter
updates on securing code and agents, vulnerability research, and product news.