Blog

Security research, tool post-mortems, and threat modeling from the Hedgerow team.

The LangChain Threat Model

The parts of a LangChain app that make it capable, its loaders, tools, stores, checkpoints, and caches, are the parts that decide what a steered model can reach. A component-level model mapped to the published CVE record, with the configuration discipline that a hardened deployment is assembled from.

Read →

How LLM Serving Infrastructure Gets Broken Into

The parts of an inference stack built to make it fast are the parts that decide who can read whose data. Ten ways that breaks, each with one check you can run against your own deployment, plus the full threat model with evidence classes and citations.

Read →

Langfail: 82 Real Bugs in a Fake MLOps Platform

We built a working MLOps platform, planted 82 vulnerabilities and 50 decoys inside it, and scored eight reproducible runs against the same answer key. The best found 91%. Four bugs were missed by every run, and none of them contains a dangerous line of code.

Read →

Closing the Seam: Cross-File Taint Analysis Without the Pro License

How we layered repository-wide, cross-file taint analysis on top of OpenGrep’s intra-file engine, so the bug that lives between two files stops being invisible. SCC-converged propagation, parameter-indexed summaries, an incremental cache, and the day the benchmark caught a zero that was impossible.

Read →

“Trust Me” Is Not a Finding: The Taint Microkernel

If frontier models are this good, why build a taint engine at all? Because a model can describe a vulnerability beautifully but can’t hand you a reproducible, auditable proof. Put the deterministic engine at the center as the kernel and let the model ride shotgun as the coprocessor.

Read →

How a Working Exploit Made Me Forget How to Threat Model

When your scanner is faster than your threat model. A post-mortem on submitting a high-severity RCE report, getting it closed as expected behavior, and what we actually missed in the process.

Read →

No posts under that topic yet.