CVE-2026-35655

mediumpriority · track · 0OT risk · elevatedEPSS 0.002 · 14 %ileDEEUUS
grimoire priorityP3 · Track
Exploitable?
—
no known exploitation
Likely / severe?
0.23% (14th) EPSS
CVSS 5.7 · medium
Is it mine?
5 products
Check your exposure
Who says so?
5 sources
cnnvd · enisa_euvd · cert_bund · nvd

EPSS · scored 2026-10-27

OpenClaw before 2026.3.22 contains an identity spoofing vulnerability in ACP permission resolution that trusts conflicting tool identity hints from rawInput and metadata. Attackers can spoof tool identities through rawInput parameters to suppress dangerous-tool prompting and bypass security restrictions.

01

cvss

Technical severity, 0–10. One row per scoring source.

6.9
010

base score 0–10 · higher = more severe · hover a vector to decode

v3.15.7mediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:N/I:H/A:Nsecondary · disclosure@vulncheck.comexploitability 2.1 · impact 3.6
v3.15.7mediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:N/I:H/A:Nsecondary · OSV
v4.06.9mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:Nsecondary · ENISA EU
v4.06.9mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · disclosure@vulncheck.com
v4.04.6mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:U/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · CVSS-BT (t0sche)
02

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Trackcoordinatorcisa_ssvcUS
03

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-807USCWE-807USCWE-863US
04

affected products (5)

Products and version ranges known to be affected.

05

advisories (2)

Vendor and ecosystem advisories describing this.

  • WID-SEC-W-2026-0856OpenClaw: Mehrere SchwachstellenDeutsch2026-03-24csaf · cert_bundDE

    Ein Angreifer kann mehrere Schwachstellen in OpenClaw ausnutzen, um beliebigen Code auszuführen, erweiterte Berechtigungen – sogar Administratorrechte – zu erlangen, Daten zu manipulieren, Sicherheitsmaßnahmen zu umgehen, vertrauliche Informationen offenzulegen, einen Denial-of-Service-Zustand herbeizuführen oder andere, nicht näher spezifizierte Angriffe durchzuführen.

  • GHSA-74wf-h43j-vvmjOpenClaw's Conflicting Tool Identity Hints Bypass Dangerous-Tool Prompting2026-03-26ghsa · osvUS

    ## Summary ACP permission resolution trusted conflicting tool identity hints from rawInput and metadata, which could suppress dangerous-tool prompting. ## Affected Packages / Versions - Package: `openclaw` (npm) - Affected: < 2026.3.22 - Fixed: >= 2026.3.22 - Latest released tag checked: `v2026.3.23-2` (`630f1479c44f78484dfa21bb407cbe6f171dac87`) - Latest published npm version checked: `2026.3.23-2` ## Fix Commit(s) - `e4c61723cd2d530680cc61789311d464ab8cdf60` ## Release Status The fix shipped in `v2026.3.22` and remains present in `v2026.3.23` and `v2026.3.23-2`. ## Code-Level Confirmation - src/acp/client.ts now fails closed when meta, rawInput, and title tool identities conflict instead of trusting spoofable raw input. - src/acp/client.test.ts ships regressions for conflicting tool identity hints and dangerous-tool prompting. OpenClaw thanks @zpbrent for reporting.

06

also known as (3)

Other names and identifiers for this entity.

07

sources

Which sources assert this record, and when.

cnnvdenisa_euvdcert_bundnvdosvNVDCVE.orgMITRE
published 2026-04-10modified 2026-06-17
08

references (13)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan