Updates

What's actually shipped, by date.

Every entry below maps to a real commit, in a real repo, verified against a real test suite before it landed — not a marketing changelog. Compiled directly from commit history, most recent first.

2026-08-25
Guardrails

Subprocess output scanning

A real, disclosed gap: a command being allowed to run said nothing about whether its output was safe to trust. A poisoned git branch name or log line could carry an injected instruction straight into an agent's context. Now scanned before it's trusted, wherever the egress firewall runs.

MCP Gateway

MCP "rug pull" detection

A tool that scans clean and gets approved once, then has its description quietly mutated after trust is established, is now tracked and flagged for review — closing a real gap our own admission check had: a same-server re-admission was previously waved through with no comparison to what was first approved.

MCP Gateway

Memory write-time checkpoint

Memory-poisoning defense previously only covered the retrieval side — scanning a record when it's recalled. Now the save side is covered too: a candidate record is screened before it's ever admitted into persistent memory, not just after.

MCP Gateway

Invocation-bound execution budgets

A tool can now be admitted with a hard cap on total call count — not a rate limit that resets, a real budget that's gone once it's spent. Built for delegating a narrow task to a sub-agent without handing it standing, indefinite access.

MCP Gateway

Alert-storm detection

A new module finds the one genuinely dangerous alert buried inside a flood of noise — the pattern real attackers use to bury a policy change in a wall of routine notifications.

MCP Gateway Guardrails Platform

Unicode normalization fix, across every detector

Fullwidth-Unicode characters could evade every ASCII-literal detection pattern in the whole prompt-injection detector — closed with NFKC normalization applied before pattern matching, ported to all three repos that vendor the detector.

Platform

Five new detection angles

Real gaps found and closed: named-colleague hearsay-approval claims, poisoned memory/knowledge-base records framed as already-vetted, plain-language sensitive-state exfiltration, sub-agent response smuggling, and fake mid-task procedural-step injection — each grounded in a specific, cited real-world technique.

2026-08-24
MCP Gateway

v0.3.0 — kill-switch integration

A duck-typed kill-switch hook now overrides every gated checkpoint when tripped, regardless of what the underlying policy would otherwise allow — a human override that wins no matter what.

Guardrails

v0.6.0 — kill-switch into Iron-Thread

The same kill-switch override, applied at Iron-Thread's own interpreter-level egress checkpoint instead of MCP tool-call granularity.

MCP Gateway

v0.2.0 — safe STDIO launch, honeytool injection

Closes the April 2026 OX Security MCP STDIO design flaw: never shell=True, executable resolved and verified to exist before launch. Plus operator-supplied honeytools mixed into a real server's real tool list.

2026-08-20 – 2026-08-21
Guardrails

Four detection categories promoted to hard-blocking

DISTRACTION_BURIAL, IAC_COMMENT_INJECTION, SCARCITY_WINDOW, and FEAR_OF_BLAME moved from advisory to auto-deny, each backed by real compliance-trial evidence before promotion — not staged on a guess.

Guardrails

Iron-Thread: opt-in file-write checkpoint

A new allow_write hook catches an agent widening its own trust boundary — writing a new or modified MCP config, permissions file, or instruction file that would get trusted on its next read.