clawlet CVE-2026-15618
LOWSeverity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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:X
Network vector confirmed; user interaction required per 4.0 UI:P; no scope change; all impacts low per 4.0 VC/VI/VA:L.
Primary rating from Vendor (vuldb).
CVSS VectorVendor: vuldb
Lifecycle Timeline
1DescriptionCVE.org
A security flaw has been discovered in mosaxiv clawlet up to 0.2.10. The affected element is the function guardExecCommand of the file tools/tool_exec.go of the component exec Safety Guard. The manipulation results in protection mechanism failure. It is possible to launch the attack remotely. The exploit has been released to the public and may be used for attacks. The reported GitHub issue was closed with the label "not planned".
AnalysisAI
Protection mechanism failure in mosaxiv clawlet up to version 0.2.10 allows remote attackers to bypass the exec Safety Guard, undermining the tool's core command-execution restriction logic. The vulnerability resides in the guardExecCommand function within tools/tool_exec.go, where insufficient enforcement of protection controls permits manipulation that should otherwise be blocked. Passive user interaction is required (CVSS 4.0 UI:P), and a public proof-of-concept exploit has been released; however, the vendor has closed the tracking GitHub issue as 'not planned', indicating no patch is forthcoming.
Technical ContextAI
clawlet is a Go-based tool maintained by mosaxiv on GitHub. The affected component is the exec Safety Guard, implemented as the guardExecCommand function in tools/tool_exec.go. This function is intended to act as a gatekeeper that validates or restricts exec-style command execution within the application. The root cause is classified under CWE-693 (Protection Mechanism Failure), meaning the defensive control itself is flawed or bypassable - rather than an overflow, injection, or authentication gap, the protective abstraction simply fails to enforce the boundary it is designed to maintain. The CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:N/UI:P) confirms the attack surface is network-reachable with low complexity, no special attack prerequisites, and no privileges required, though some passive user interaction is involved.
Affected ProductsAI
All versions of mosaxiv clawlet through 0.2.10 are affected, specifically within the exec Safety Guard component (guardExecCommand in tools/tool_exec.go). The project is available at https://github.com/mosaxiv/clawlet/. No CPE string was provided in the source data; the affected product is inferred from the NVD references and VulDB submission. No patched version exists as the vendor closed the issue without remediation.
RemediationAI
No vendor-released patch has been identified at time of analysis - the upstream GitHub issue (https://github.com/mosaxiv/clawlet/issues/12) was closed with the label 'not planned', meaning the maintainer does not intend to fix this vulnerability. Organizations using clawlet should evaluate whether to replace or fork the project. As a specific compensating control, restrict network access to any service or pipeline invoking clawlet so that only trusted, authenticated callers can reach the code paths that invoke guardExecCommand; this reduces the effective attack vector from network-accessible to a controlled internal boundary, trading accessibility for reduced exposure. Additionally, treat the exec Safety Guard as untrusted and layer an external command-execution sandbox (e.g., OS-level seccomp profiles, container isolation, or AppArmor/SELinux policies) around any process invoking clawlet, since the internal guard cannot be relied upon. Migrating to an alternative, actively maintained exec-restriction library is the most durable remediation path.
Same weakness CWE-693 – Protection Mechanism Failure
View allSame technique Information Disclosure
View allShare
External POC / Exploit Code
Leaving vuln.today