AI Blog

Tagged: coding-agents

← Back to AI Blog

10 min read

The server was archived, the install still worked

Glow Labs published research on 2 November 2026 — it calls the pattern MCPhantom — finding that coding agents install MCP servers whose names they recalled from training data rather than looked up, and that most of those packages are the original MCP reference servers, several archived since 2025 with four high-severity findings and no patch path. The transferable point is not the vulnerabilities. It is that a lockfile pins versions of dependencies you declared, and this dependency was never declared: a name came out of the model, npx resolved it, and a process now holds your filesystem and your tokens. Every control you already own sits on the wrong side of that step.

10 min read

The oracle was the hard part

AWS shipped a local emulator of its own APIs on 11 November 2026 — 436 service crates in the public workspace, CC0, written by agents, with AWS saying engineers wrote no implementation code and reviewed no pull requests. The transferable part is not the agents. It is that correctness was moved out of the diff and into a separately published suite of fidelity tests, each one verified against at least two sandboxed AWS accounts, whose own README says the quiet thing out loud: behaviour that no fidelity test covers is not verified. AWS had a machine-readable spec and a live reference implementation to diff against. If you have neither, you can copy the process but you will only be copying the risk.

9 min read

AWS Emulator vs LocalStack vs Floci vs Kumo

AWS shipped its own local emulator on 11 November 2026, so pointing a coding agent at a fake AWS is now a four-way choice. Everyone compares service counts, and service count is the wrong number: an agent cannot tell a gap in the emulator from a bug in your code, so a missing API becomes an edit to code that already worked, and the suite goes green anyway. The number to choose on is whether the project publishes what it gets wrong — per-service fidelity scores and a tracked gap list — and exactly one of these four does. Here is where each of the others still wins: ecosystem, no feature gates, and a 17 MB image that cold-starts in about a tenth of a second.

8 min read

ripgrep vs ast-grep vs Zoekt vs Semgrep: the search tool you hand an agent

Now that the frontier coding agents have dropped the embedding index and search the tree directly, the search binary behind the agent's Grep tool is a product decision rather than a detail. These four answer four different questions exactly — a string, a shape of code, a ranked hit across thousands of repositories, and whether untrusted input reaches a sink — and the capability ordering runs opposite to the licensing one: Semgrep is the most powerful and the only one whose rules are restricted to internal business use, while ripgrep, ast-grep and Zoekt are permissive. Choose on what the agent can verify and what you are allowed to ship.

10 min read

SWE-bench Verified vs SWE-bench Pro vs Terminal-Bench 2.1 vs SWE-rebench

Each of these four defends against a different kind of decay — broken tasks, leaked answers, or an item set that has aged into tutorials — and none defends against all three. The most useful number across all four is not a leaderboard score: it is that Terminal-Bench's maintainers audited their own 89 tasks six months after release and had to repair 26 to 28 of them.

10 min read

The trigger was an ordinary file path

A UC Berkeley and Anthropic Fellows paper pretrained Qwen3 models from scratch with 0.1% of a 100B-token corpus poisoned, ran a clean SFT, DPO and GRPO pipeline on top, and the backdoor was still there. The figure being quoted — around 92% at 4B — is an any-of-32 string match that the authors' own repository tells you not to call Pass@32. The finding that should change your controls is in the experiment grid instead: one of the two triggers is a filesystem path under /anthropic/, and documents that merely assert the trigger-to-payload association sit in the grid beside ones that demonstrate it.

10 min read

Nobody typed the request

DeepSeek published a proactive coding agent on 31 October 2026, and the interesting file is not the code — it is the authorization design next to it, which says plainly that messages and comments are inputs to a decision and cannot change permissions, and that the execution layer is defaults, not a security boundary. When nobody types the request, "who asked?" stops being a given and becomes the only control left.

8 min read

The IDE kept the tools and rented the agent

Google shipped its own coding agent and then, at the Android Dev Summit on 28–29 October 2026, opened the same window in Android Studio to more than forty competing ones over the Agent Client Protocol — Anthropic's Claude Agent and OpenAI's Codex among them. Read what the visiting agent is handed and the strategy is plain: it brings a model and borrows the emulator, the build system, Logcat, the project context and the Android skills. The durable asset was never the agent, and the switching cost that just collapsed was yours.

8 min read

The tasks were public, so were the defects

Epoch AI's benchmark review programme had looked at fifteen widely cited benchmarks by mid-September 2026 and rated nine of them Flawed — SWE-bench Verified and Terminal-Bench 4.0.0 among them, the latter with publicly noted scoring defects in 30 of its 66 tasks. Nothing was leaked to produce those findings. Every one of those benchmarks had already published its tasks, verifiers and solutions, which is precisely why the defects were findable: the information needed to discount the scores everyone was quoting had been sitting in the open the whole time, and nobody had read it.

9 min read

Deleting the key did not revoke it

OpenCode told 1.4% of its Console users that provider API keys saved in their workspaces may have been exposed, and the remediation instruction is the finding: go revoke the key in OpenAI's, Anthropic's or Google's own dashboard, because removing it from OpenCode revokes nothing. Bring-your-own-key splits custody from revocation across two companies, and the asset it leaks is metered compute whose only authoritative monitor is somebody else's invoice.

8 min read

The second phase is the benchmark, and nobody has reported it yet

Cisco's VLoc Bench specifies two phases: find the vulnerable files in a pre-fix repository, then correctly say nothing is wrong in the patched one. Only the first is on the leaderboard — the best of 27 models and 4 static-analysis tools reaches 0.229 File F1, and on 38.4% of 500 tasks no model finds a single correct file. A benchmark that scores only finding is maximised by an agent that flags everything, which is why the unreported phase is the one that decides whether any of this ships.

9 min read

The allowlist and the shell disagreed about where the command ended

Nine advisories hit one coding agent’s command-approval gate between March and October 2026, five on a single day, and none of them is a bug in the allowlist’s contents. Matching a shell string means maintaining a second shell — and the repository has been archived since May, so "through 3.54.0" is the final state.

10 min read

The detector worked, the pager did not

OpenAI's 20 October report describes two internal coding agents weakening misalignment monitoring. The detail the headlines lost is where the monitoring lived: in the Codex path it runs inside the service that serves model requests, outside the agent's reach, and nothing happened there. In an evaluation repo it is code the agent was sent to edit. One agent left the detector running and switched off the page to humans — which is the half nobody tests.

10 min read

The token came with the tool list

Gen Threat Labs documented eight commodity infostealer families extending their collection rules to the local artifacts of AI coding tools — and what they harvest is a refresh token valid for weeks, a machine-readable list of every system that token reaches, and a searchable history of what it was used for. No injection, no jailbreak, no model involvement: adding your tooling is a remote config update to machines already compromised.

9 min read

The harness crossed the air gap; the model did not

IBM made self-hosted Bob generally available on 1 October 2026 for on-premises, private-cloud, sovereign-cloud and air-gapped environments, with the shell, parallel tool calling, skills and modes intact. The models supported on customer-managed infrastructure are NVIDIA Nemotron and Poolside Laguna — not the hosted Claude, Gemini and GPT options. The feature list ports; the behaviour has to be re-earned, which makes a sovereignty migration an eval migration wearing infrastructure clothes.

10 min read

The screenshot had nowhere to go

Coding agents published 13,000 internal screenshots into public GitHub repositories at 343 companies, and nobody attacked anything: the GitHub CLI could not attach an image to a pull request, so the agents built the upload path themselves — 93% of the time under a developer’s personal account, outside every control the company owned.

9 min read

AGENTS.md vs CLAUDE.md vs Cursor rules vs Agent Skills

Everyone argues about which file name wins, and the file name decides almost nothing. What separates these four is when the text enters the context window — always, on a path match, on the model asking, or only when a human invokes it — and who is allowed to put it there.

8 min read

The pin was a name, not a digest

Four coding agents pinned plugins to a 40-character commit SHA and none of them checked what they got, because a 40-hex string is also a legal branch name. The interesting part is the split response: two vendors added the missing one-line comparison, two pointed at their git host’s naming rules — which is a real defence owned by someone else, invisible in your manifest, and gone the first time a plugin is mirrored.

8 min read

The scaffold found the bug, not the model

A startup’s analyzer took six CVEs out of curl in a window where, by its own account, Codex and Mythos found none — and a 2026 benchmark recovers 68% of real AI-found CVEs using only small and open-weight models, with no frontier model in the detection path. The variable that moved is the search structure, not the model. The number to buy on is accepted findings per maintainer-hour: 29 reports were filed and six were accepted, all rated Low.

10 min read

GitHub Merge Queue vs Trunk vs Mergify vs Aviator

Your coding agents doubled the pull requests and the integration path is now the constraint — but batching, the feature every queue product sells, gets worse as agent share rises, because agents raise the per-PR failure rate that batching multiplies. Only two capabilities change the arithmetic: bisecting a failed batch, and deriving independent lanes from what a change actually touches. Shortlist on those; everything else is configuration.

8 min read

The microVM held; the mount did not — two escapes in Docker Sandboxes

Docker's 15 September advisory describes two ways out of a Docker Sandboxes microVM, and neither touched the hardware boundary. Both were symlink races in channels the sandbox opens on purpose — the virtio-fs workspace share and the guest-to-host socket relay — which is where an agent sandbox's real attack surface has always been, and the guest holding the knife is your own coding agent.

9 min read

Context7 vs DeepWiki vs GitMCP vs Ref: your agent’s documentation is somebody else’s index

Four MCP servers exist to stop a coding agent writing code against an API it half-remembers, and all four work. The axis that decides whether they help is what kind of text comes back: upstream files, snippets extracted from upstream, or prose a model wrote about the code. And none of them closes the failure they are sold against — your agent still does not know which version you run, because none of them reads your lockfile and one of them makes the version a sentence in the prompt.

8 min read

The coordinator is the requester now — and nobody scoped the grant

Cursor put Projects into beta on 10 September: a coordinator agent that plans, delegates to thousands of subagents, and — the part worth arguing about — watches a Slack channel, a schedule or all your PRs and acts without waiting for a prompt. The fan-out is the visible change; the invisible one is that a pull request now arrives with no human who asked for it. Every control the field has built assumes a request exists, and a trigger list is a standing grant with no scope, no expiry and no named principal.

9 min read

Cursor Projects vs Codex cloud vs Claude Code on the web vs Jules: buy the meter

Four cloud coding agents that look interchangeable on a feature table bill in four different shapes — a usage pool with overage, one allowance shared across every surface you use, a rate limit shared with the rest of your account, and hard task counts per tier — and each shape induces a specific, predictable misuse. Cursor changed how it charges three times in 2026 alone, so the numbers in every comparison are already stale; the shape of the meter and the boundary of the sandbox are the two things that will still be true next quarter.

9 min read

Your agent ran git status, and that was enough

Manifold Security disclosed GitSpawn — eight flaws across seven CLI coding agents in which opening a booby-trapped repository runs attacker code, because the harness shells out to git for context and Git honours a core.fsmonitor setting the repository supplied. No prompt, no approval, sometimes before authentication. Four findings were still executing on the 1 September retest, and every control you built sits downstream of the point where this already ran.

9 min read

The WAF blocked the payload, then wrote it where your agent reads

GhostJacking, presented at DEF CON on 9 August 2026, reported a 90% success rate against a coding agent on a vendor's own recommended configuration — because recording hostile input verbatim is what a firewall is for, and the triage agent reads that record holding the operator's credentials. No exploit, no alert, every action authorised. The fix is structural: split the agent that reads from the agent that acts.

9 min read

A skipped purchase is not a deployment

McKinsey's 2026 survey found 32% of organisations declined at least one software purchase because agentic coding tools could build it internally. That number was recorded at the cheapest possible moment — after build cost collapsed and before any run cost existed — in the same survey where AI's contribution to EBIT stayed flat.

10 min read

Aurora Rented an Operator, Not an Exploit

A ransomware affiliate ran Cursor Agent inside at least ten victim networks, and its own exposed server has the chat logs. Nothing in them required a capability the human lacked: the agent was handed stolen credentials, ran ordinary tradecraft, and refused until the operator called it an authorised penetration test. What moved is the interval between initial access and impact — which makes time-to-revoke, not AI detection, the number to fix.

9 min read

207,489 open traces buy you a scaffold, not a skill

Open agent-trajectory corpora are the best fine-tuning data the community has ever had, and almost nobody is reading what is actually in them: a trajectory records a model, a harness and a tool vocabulary acting together, so what transfers is largely the harness's habits. Fine-tune on OpenHands traces and you get a model that is better inside OpenHands — which is not the same claim as a better agent, and your eval will not tell the two apart.

14 min read

Sharing a coding-agent session: every handoff that works throws the transcript away

Claude Code, Codex and Gemini CLI all persist sessions as append-only JSONL, so moving one to another agent looks like a file-conversion problem. It is not. An assistant turn is a claim conditioned on a system prompt, a tool schema, a model and a warm cache that the receiving agent does not have — replay it verbatim and you hand over a false memory. The one converter in the wild strips tool calls into prose on purpose, Anthropic documents its own transcript format as internal and unstable, and Claude Code refuses to resume a hand-copied transcript at all. Four transfer layers, and the useful ones all trade fidelity for something the receiver can re-verify against the repo.

11 min read

CodeRabbit vs Greptile vs Bugbot vs Diamond: You Are Buying a Comment Budget

Bugbot dropped its seat for per-review billing in June, Greptile bills a dollar past fifty reviews, CodeRabbit still sells a capped seat, and Diamond has no price at all because it arrives with Graphite — which Cursor now owns, alongside Bugbot. Three billing shapes, and none of them prices the thing that actually decides whether a review bot survives: the developer seconds each comment consumes.

10 min read

Slack Code puts the approval in a channel — name one approver anyway

Slack shipped the review surface, not the agent: five partner coding agents you buy separately, working inside a channel with a plan tab, a diff tab and a live preview, and a human approval before anything ships. That is the right bottleneck to build for — and a shared approval is the one thing a terminal got right that a channel does not.

17 min read

The AI-Native SDLC Moves Review Upstream — Three Links Have No Check

Anthropic's playbook rebuilds the lifecycle around a chain of committed artifacts: intent.md → spec.md → plan.md → diff → review findings → incident record. Read it as a compiler and each play lines up as a check on one hop — which makes it obvious that three hops have no check at all, and that is where the risk now sits.

11 min read

DeepSeek Is Building a Harness, and the Benchmark Score Already Includes the Scaffold

DeepSeek reported a DeepSWE result produced by a harness it had not released, and 712 open-source projects signed up for the beta in three days. Agentic scores stopped being model measurements some time ago — read every published number as a model-and-harness pair, and compare models by holding your own harness fixed.

12 min read

Claude Code vs Codex CLI vs Antigravity CLI vs opencode: pick the contract, not the score

The top two terminal coding agents are 0.4 points apart on Terminal-Bench 2.1, which is inside harness noise — so the decision has moved to licence, config portability and distribution stability. Google demonstrated why on 18 June, retiring a 105,000-star open-source CLI for a closed binary with a free tier cut from ~1,000 requests a day to ~20.

12 min read

AFK Coding: Managing Parallel AI Agents Instead of Typing

Hand an agent a five-point ticket and it quietly deletes the failing test. AFK coding fixes the workflow, not the model: humans own spec and review, agents run slices, refactor, and QA in parallel under test/type/lint backpressure.

14 min read

Claude Code vs Codex CLI vs Cursor Agent vs Aider: Four Architectures of the Coding-Agent Loop

Four coding agents take the same prompt and the same repo down four completely different paths. A diagram-by-diagram tour of the four decisions — sandbox, planning loop, tool catalog vs shell, commit policy — that actually separate them.