CVE
CVE-2026-61536, CVE-2026-54912, CVE-2026-54914, CVE-2026-54143, CVE-2026-54141, CVE-2026-54146, CVE-2026-54145, CVE-2026-54142, CVE-2026-54140, CVE-2026-49393, CVE-2026-97693, CVE-2026-123018, CVE-2026-82033
CWE
CWE-94, CWE-787, CWE-125, CWE-306, CWE-269, CWE-214, CWE-470
Affected Surface
- PyPI `banks` (`github.com/masci/banks`, LlamaIndex prompt template library) versions `<= 2.4.2` (`CVE-2026-61536` / `GHSA-64vx-6h2c-rjh7`, CVSS 7.5 High, fixed in `2.4.3`)
- Bytecode Alliance WebAssembly Micro Runtime (`wasm-micro-runtime/wasm-micro-runtime`, `iwasm`) versions `< 2.4.5` (`CVE-2026-54912` CVSS 8.8 High and `CVE-2026-54914` CVSS 8.3 High, fixed in `WAMR-2.4.5`)
- Rust / Tauri AI agent harness `openhuman` (`github.com/tinyhumansai/openhuman`) versions `< 0.56.0` (`CVE-2026-49393`), `< 0.57.5` (`CVE-2026-54145`, `CVE-2026-54146`), and `< 0.57.13` (`CVE-2026-54140`, `CVE-2026-54141`, `CVE-2026-54142`, `CVE-2026-54143`, up to CVSS 9.8 Critical)
- Python AI agent platforms `Yuxi` (`github.com/xerrors/Yuxi` `>= 0.6.0.beta1, < 0.7.1`, `CVE-2026-97693` / `GHSA-qpm5-6332-9445`, CVSS 9.9 Critical), `DB-GPT` (`github.com/eosphoros-ai/DB-GPT` `<= 0.8.2`, `CVE-2026-123018`, CVSS 8.3 High), and `DeepSeek Harness` (`github.com/deepseek-ai/deepseek-harness` `< 0.1.2-alpha.2`, `CVE-2026-82033`, CVSS 8.4 High)
TL;DR
Between 4 November (19:17 UTC) and 5 November 2026 (18:17 UTC), NVD and the GitHub Advisory Database published 13 high- and critical-severity vulnerabilities across six AI agent runtimes, prompt-templating packages, and WebAssembly engines:
- LlamaIndex
banks <= 2.4.2CompletionExtensionimportlibRCE (CVE-2026-61536/GHSA-64vx-6h2c-rjh7, CVSS 7.5 High, fixed in2.4.3):banks2.4.2switched its Jinja2 environment toSandboxedEnvironmentto fixCVE-2026-44209, but leftCompletionExtension._get_tool_callable()insrc/banks/extensions/completion.pyuntouched. Because{% completion %}parsesToolJSON objects from the rendered template body and resolvedtool.import_pathviaimportlib.import_module(module_name)andgetattr(mod, func_name)without an allowlist, an attacker controlling a template or tool metadata string could set"import_path": "os.system"(or"subprocess.getoutput") and execute arbitrary OS commands when the LLM emitted a matchingtool_callsentry. - Bytecode Alliance WebAssembly Micro Runtime (
WAMR < 2.4.5,CVE-2026-54912CVSS 8.8 High &CVE-2026-54914CVSS 8.3 High): Incore/iwasm/interpreter/wasm_loader.c, the two-pass fast interpreter loader capped constant-table deduplication scans atFAST_INTERP_CONST_DEDUP_SCAN_MAX(32), causing Pass 1 and Pass 2 to disagree on whether a constant was already deduplicated once intervening constants pushed the table past 32 entries and overflowing the heap-allocated constant table (CVE-2026-54912, public PoC gistshumbo/b710c35b005ed871447fce385d1ab760). Incore/iwasm/libraries/libc-wasi/libc_wasi_wrapper.c,wasi_poll_oneoff()checkedvalidate_app_addr(out_offset, sizeof(wasi_event_t))for a single event struct instead ofnsubscriptions * sizeof(wasi_event_t)(CVE-2026-54914). - OpenHuman AI agent harness (
< 0.56.0/< 0.57.5/< 0.57.13, 7 CVEs up to CVSS 9.8 Critical): Prior to0.56.0, the Rust core server required bearer auth on HTTPPOST /rpcbut exposed the identical JSON-RPC methods unauthenticated over Socket.IOrpc:request(CVE-2026-49393, CVSS 8.4). Prior to0.57.5, the macOS Tauri desktop binary spawnedopenhuman-corewith--token <OPENHUMAN_CORE_TOKEN>inargv, exposing the root RPC secret to any local process viaps/sysctl(CVE-2026-54146, CVSS 8.8), and used the static bearer token as the approval-gate session ID (CVE-2026-54145, CVSS 8.8). Prior to0.57.13, external chat channels (such as Yuanbao DMs) could create persistent scheduled cron jobs that re-ran with full host tool privileges (CVE-2026-54143CVSS 9.8 Critical andCVE-2026-54141CVSS 9.0 Critical). - Yuxi (
< 0.7.1,CVE-2026-97693CVSS 9.9 Critical), DB-GPT (<= 0.8.2,CVE-2026-123018CVSS 8.3 High), and DeepSeek Harness (< 0.1.2-alpha.2,CVE-2026-82033CVSS 8.4 High): Yuxi placed agent code-execution containers on the same Docker network as internal Postgres, MinIO, and sandbox-provisioner services without authentication (CVE-2026-97693); DB-GPT’sexecute_code()incode_utils.pycheckedif not use_docker or in_docker_container:(wherein_docker_container = os.path.exists("/.dockerenv")), silently bypassing its own Docker sandbox whenever DB-GPT itself ran inside a container (CVE-2026-123018); and DeepSeek Harness exposed its local HTTP/WebSocket host RPC API without a bearer token (CVE-2026-82033).
What to do now: Upgrade banks to >= 2.4.3 (2.5.1 latest), WAMR (iwasm) to >= 2.4.5, OpenHuman to >= 0.57.13, Yuxi to >= 0.7.1, and DeepSeek Harness to >= 0.1.2-alpha.2. On DB-GPT (<= 0.8.2), do not expose port 5670 to untrusted callers and disable CodeAction native subprocess.run fallback inside containers.
Affected packages and projects
| Ecosystem | Package / Project | CVE / GHSA | Severity | Affected versions | Fixed version | Vulnerable component |
|---|---|---|---|---|---|---|
| PyPI | banks (masci/banks) | CVE-2026-61536 (GHSA-64vx-6h2c-rjh7) | CVSS 7.5 High | <= 2.4.2 | 2.4.3 (2.5.1 latest) | src/banks/extensions/completion.py (_get_tool_callable) |
| C / WASM | wasm-micro-runtime (WAMR) | CVE-2026-54912, CVE-2026-54914 | CVSS 8.8 / 8.3 High | < 2.4.5 | 2.4.5 | core/iwasm/interpreter/wasm_loader.c, libc_wasi_wrapper.c (wasi_poll_oneoff) |
| Rust / Tauri | openhuman (tinyhumansai/openhuman) | CVE-2026-54143, CVE-2026-54141, CVE-2026-54142, CVE-2026-54140 | CVSS 9.8 / 9.0 / 8.7 / 8.3 | < 0.57.13 | 0.57.13 | src/openhuman/agent/turn_origin.rs, src/openhuman/cron/scheduler.rs, mcp prompt assembly |
| Rust / Tauri | openhuman | CVE-2026-54146, CVE-2026-54145, CVE-2026-49393 | CVSS 8.8 / 8.8 / 8.4 High | < 0.57.5 (54146, 54145); < 0.56.0 (49393) | 0.57.5, 0.56.0 | core_process.rs (OPENHUMAN_CORE_TOKEN argv), approval/gate.rs, src/core/socketio.rs |
| Python / Docker | Yuxi (xerrors/Yuxi) | CVE-2026-97693 (GHSA-qpm5-6332-9445) | CVSS 9.9 Critical | >= 0.6.0.beta1, < 0.7.1 | 0.7.1 | docker/sandbox_provisioner/app.py, docker-compose.yml sandbox network isolation |
| Python | DB-GPT (eosphoros-ai/DB-GPT) | CVE-2026-123018 | CVSS 8.3 High (9.8 CNA) | <= 0.8.2 | Unpatched upstream (mitigate via network auth & sandbox config) | packages/dbgpt-core/src/dbgpt/util/code_utils.py (execute_code) |
| Rust / Web | deepseek-harness | CVE-2026-82033 | CVSS 8.4 High | < 0.1.2-alpha.2 | 0.1.2-alpha.2 | Web profile HTTP and WebSocket Host RPC API (commit 3e24087bfaea) |
Technical analysis
1. CVE-2026-61536: Why Jinja2 SandboxedEnvironment did not stop banks {% completion %} RCE
In banks 2.4.2, the maintainers fixed a classic Jinja2 SSTI (CVE-2026-44209 / GHSA-gphh-9q3h-jgpp) by switching src/banks/env.py from jinja2.Environment to jinja2.sandbox.SandboxedEnvironment. However, banks also provides a {% completion %} block tag (src/banks/extensions/completion.py) that lets templates turn Python functions into LLM tool schemas using the | tool filter.
Prior to 2.4.3 (commit e443f112b80a, PR #75), the | tool filter serialized a Tool Pydantic model containing "import_path": f"{func.__module__}.{func.__qualname__}" as JSON inside the rendered block. When the LLM responded with a tool_calls entry, CompletionExtension._get_tool_callable() deserialized the Tool JSON from the rendered text and imported whatever dotted path was written in tool.import_path:
--- a/src/banks/extensions/completion.py
+++ b/src/banks/extensions/completion.py
@@ -41,6 +40,14 @@ class CompletionExtension(Extension):
tags = {"completion"} # noqa
+ # Maps tool function names to the actual callables registered via the `tool`
+ # filter. Using an explicit registry avoids calling `importlib.import_module`
+ # on attacker-controlled strings embedded in template text.
+ _callable_registry: ClassVar[dict[str, Callable[..., Any]]] = {}
@@ -143,12 +150,11 @@ class CompletionExtension(Extension):
def _get_tool_callable(self, import_path: str) -> Callable:
- items = import_path.split(".")
- module_name = ".".join(items[:-1])
- func_name = items[-1]
- mod = importlib.import_module(module_name)
- return cast(Callable, getattr(mod, func_name))
+ try:
+ return self._callable_registry[import_path]
+ except KeyError as exc:
+ msg = f"Tool '{import_path}' is not registered. Only callables passed through the `tool` filter may be invoked."
+ raise ValueError(msg) from exc
Because {% completion %} accepted any JSON block matching the Tool schema inside the rendered template body, an untrusted template did not need Jinja2 attribute traversal at all: embedding a raw JSON Tool definition with "import_path": "os.system" caused _get_tool_callable("os.system") to return os.system and pass the LLM’s tool_call.function.arguments directly to it.
2. CVE-2026-54912 and CVE-2026-54914: WAMR 2.4.5 fast-interpreter constant table overflow and wasi_poll_oneoff out-of-bounds write
In Bytecode Alliance’s WebAssembly Micro Runtime (WAMR < 2.4.5), when WASM_ENABLE_FAST_INTERP != 0, wasm_loader.c runs a two-pass loader: Pass 1 counts unique constants (const_cell_num) to allocate a single contiguous constant buffer, and Pass 2 populates the buffer. To avoid $O(n^2)$ scans on modules with thousands of constants, WAMR introduced FAST_INTERP_CONST_DEDUP_SCAN_MAX (32), scanning for duplicates only while const_count < 32.
However, Pass 1 incremented const_count for all constants as it scanned instructions, whereas Pass 2 emitted function parameter/local zero-initializers and branch constants in a slightly different order. Once a function crossed 32 constants, a constant that was deduplicated in Pass 1 (while const_count < 32) could be evaluated in Pass 2 after const_count >= 32, skipping deduplication, allocating a new slot in Pass 2 that Pass 1 never budgeted for, and overflowing the heap buffer (CVE-2026-54912, fixed in commit b1353b5e8983).
In the same WAMR-2.4.5 release, commit b49d10eac417 fixes CVE-2026-54914 in wasi_poll_oneoff() across both libc-wasi and libc-uvwasi:
--- a/core/iwasm/libraries/libc-wasi/libc_wasi_wrapper.c
+++ b/core/iwasm/libraries/libc-wasi/libc_wasi_wrapper.c
@@ -887,9 +887,12 @@ wasi_poll_oneoff(wasm_exec_env_t exec_env, const wasi_subscription_t *in,
wasm_module_inst_t module_inst = get_module_inst(exec_env);
- if (!validate_native_addr((void *)in, sizeof(wasi_subscription_t))
- || !validate_native_addr(out, sizeof(wasi_event_t))
+ if (((uint64)nsubscriptions * sizeof(wasi_subscription_t) > UINT32_MAX)
+ || !validate_native_addr((void *)in,
+ (uint32)nsubscriptions * (uint32)sizeof(wasi_subscription_t))
+ || !validate_native_addr(out,
+ (uint32)nsubscriptions * (uint32)sizeof(wasi_event_t))
|| !validate_native_addr(nevents, sizeof(uint32)))
return (wasi_errno_t)-1;
Previously, a WASI module could place in or out 1 struct before the end of linear memory and pass nsubscriptions > 1, reading or writing host heap memory immediately after the WASM linear memory mapping.
3. CVE-2026-123018 (DB-GPT), CVE-2026-97693 (Yuxi), and CVE-2026-54143 (OpenHuman): AI agent sandbox and channel escapes
In DB-GPT (<= 0.8.2), CodeAssistantAgent extracts triple-backtick python, bash, and sh blocks from LLM output and passes them to execute_code() in packages/dbgpt-core/src/dbgpt/util/code_utils.py. To decide whether to run the code inside a disposable Docker container or directly on the host with subprocess.run, execute_code() ran:
# packages/dbgpt-core/src/dbgpt/util/code_utils.py (DB-GPT <= 0.8.2)
in_docker_container = os.path.exists("/.dockerenv")
if not use_docker or in_docker_container:
# Runs LLM-generated bash/python directly inside the DB-GPT server process!
result = subprocess.run([cmd, filepath], capture_output=True, text=True, ...)
Because official DB-GPT deployments run inside Docker (where /.dockerenv always exists), in_docker_container is True, short-circuiting the if condition and running every LLM-generated script directly inside the DB-GPT application container (with full access to DB-GPT’s database credentials and model API keys).
Similarly, in Yuxi (< 0.7.1, CVE-2026-97693), commit b5b5713e6e63 isolates agent sandbox containers onto a dedicated internal Docker network (sandbox_net), requires an X-Sandbox-Provisioner-Token header on the sandbox provisioner API, and strips backend database and API credentials from sandbox environments. And in OpenHuman (< 0.57.13, commit 3a7180da7765), introducing TurnOrigin prevents messages arriving over external chat channels (CVE-2026-54141, CVE-2026-54143) from invoking privileged host tools or scheduling cron jobs that later execute as a local user turn.
Detection and remediation
# 1. Check Python environments and lockfiles for banks <= 2.4.2 and dbgpt <= 0.8.2
pip show banks dbgpt 2>/dev/null || true
rg -n '(banks|dbgpt)' requirements*.txt pyproject.toml uv.lock poetry.lock Pipfile.lock 2>/dev/null
# 2. Check WAMR (iwasm), OpenHuman, Yuxi, and DeepSeek Harness versions
iwasm --version 2>/dev/null || true
rg -n 'wasm-micro-runtime|openhuman|xerrors/Yuxi|deepseek-harness' Cargo.lock go.mod docker-compose*.yml Dockerfile* 2>/dev/null
- Upgrade
banksto>= 2.4.3(pip install -U "banks>=2.4.3"): Verify that templates using{% completion %}register all tools through the| toolfilter rather than raw JSONimport_pathstrings. - Upgrade WAMR to
>= 2.4.5: Any service embeddinglibiwasm/vmlibto run untrusted WebAssembly modules with fast interpreter or WASI enabled must update toWAMR-2.4.5. - Upgrade OpenHuman to
>= 0.57.13, Yuxi to>= 0.7.1, and DeepSeek Harness to>= 0.1.2-alpha.2: On OpenHuman deployments, audit scheduled cron jobs created prior to upgrading (CVE-2026-54143). On DB-GPT deployments (<= 0.8.2), place port5670behind authentication and patch or disableCodeActionsoin_docker_containerdoes not fall back to hostsubprocess.run.
Timeline
- 2026-06-18 to 2026-08-25: Maintainers commit fixes in
masci/banks(e443f112b80a,v2.4.3),wasm-micro-runtime(b1353b5e8983andb49d10eac417,WAMR-2.4.5),tinyhumansai/openhuman(b1bbc53fceed,3a7180da7765,v0.56.0/v0.57.5/v0.57.13),xerrors/Yuxi(b5b5713e6e63,v0.7.1), anddeepseek-ai/deepseek-harness(3e24087bfaea,dsh-v0.1.2-alpha.2). - 2026-11-04 (
19:17to22:18 UTC): NVD publishesCVE-2026-82033(DeepSeek Harness) andCVE-2026-97693(Yuxi). - 2026-11-05 (
12:17to18:17 UTC): NVD and the GitHub Advisory Database publishCVE-2026-123018(DB-GPT),CVE-2026-49393andCVE-2026-54140..54146(OpenHuman),CVE-2026-61536/GHSA-64vx-6h2c-rjh7(banks), andCVE-2026-54912/CVE-2026-54914(WAMR).
From research to remediation
Check whether this pattern exists in your codebase
Turn this research into a remediation workflow. Scan dependencies and package manifests for similar supply-chain risk, then prioritize fixes with reachability context.
References
- GitHub Advisory GHSA-64vx-6h2c-rjh7 and commit e443f112b80a (CVE-2026-61536: Banks CompletionExtension importlib RCE)
- WAMR 2.4.5 commits b1353b5e8983 (CVE-2026-54912: fast-interp const table overflow) and b49d10eac417 (CVE-2026-54914: wasi_poll_oneoff)
- OpenHuman commits b1bbc53fceed (CVE-2026-49393), c5ff4a3516a9 (CVE-2026-54145), and 3a7180da7765 (CVE-2026-54141..54143)
- Yuxi commit b5b5713e6e63 (CVE-2026-97693 / GHSA-qpm5-6332-9445) and DeepSeek Harness commit 3e24087bfaea (CVE-2026-82033)
- DB-GPT issue #3287 and advisory (CVE-2026-123018: CodeAction /.dockerenv sandbox bypass)