The vulnerability of the Nextcloud Talk plugin with the AI agent OpenClaw (previously known as ClawdBot or MoltBot) allows a hacker to bypass existing security mechanisms.

The vulnerability of the Nextcloud Talk plugin and the AI agent OpenClaw previously known as ClawdBot or MoltBot is related to deficiencies in the authentication process. Exploiting this vulnerability allows a malicious actor to bypass existing security mechanisms remotely...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) involves unlimited distribution of resources, allowing a hacker to cause a service failure.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to the unlimited distribution of resources due to incorrect decoding based on the Base64 standard. Exploiting this vulnerability can allow a hacker to cause service failures...

The vulnerability of the WebSocket-server of the Gateway AI-agent OpenClaw (formerly known as ClawdBot or MoltBot) allows a perpetrator to execute arbitrary code.

The vulnerability of the WebSocket-server of the OpenClaw AI agent formerly known as ClawdBot or MoltBot is related to an uncontrolled element in the search path. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code...

The vulnerability of the Telegram channel for the AI agent OpenClaw (formerly ClawdBot or MoltBot) allows a hacker to bypass existing security mechanisms.

The vulnerability of the Telegram channel of the AI agent OpenClaw formerly ClawdBot or MoltBot is related to an incorrect authorization process based on a list of permitted senders. Exploiting this vulnerability allows a malicious actor to bypass existing security mechanisms remotely...

The vulnerability of the Webhook component of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) allows a violator to trigger a service failure.

The vulnerability of the Webhook component of the AI agent OpenClaw formerly known as ClawdBot or MoltBot relates to the unlimited distribution of resources. Exploiting this vulnerability could allow a remote attacker to cause service interruptions...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) arises from an incorrect restriction on the path name to the catalog, allowing attackers to write arbitrary files.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to an incorrect restriction on the path name to the catalog. Exploiting this vulnerability allows a malicious actor to write arbitrary files...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) is related to the use of the outdated cryptographic algorithm SHA-1. This vulnerability allows a hacker to disclose the protected information.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to the use of the outdated cryptographic algorithm SHA-1. Exploiting this vulnerability allows a remote attacker to disclose the protected information...

PT-2026-38246

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.4.22 Description A time-of-check/time-of-use TOCTOU race condition exists in the OpenShell filesystem bridge. This issue allows attackers to use symlink swaps during filesystem operations to bypass sandbox...

The vulnerability of the BlueBubbles plugin for the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) allows a hacker to bypass existing security mechanisms.

The vulnerability of the BlueBubbles plugin for the AI agent OpenClaw previously known as ClawdBot or MoltBot is related to the lack of authentication for a critical function. Exploiting this vulnerability allows a malicious actor to bypass existing security mechanisms remotely...

The vulnerability of the fetchWithGuard() function in the AI agent OpenClaw (formerly ClawdBot or MoltBot) allows a violator to trigger a service failure.

The vulnerability of the fetchWithGuard function in the AI agent OpenClaw formerly ClawdBot or MoltBot is related to the unlimited distribution of resources. Exploiting this vulnerability could allow a remote attacker to cause service failures...

45,000 Attacks, 5,300+ Backdoors Tied to China-Linked Cybercrime Operation

SOCRadar researchers have uncovered a massive Chinese cybercrime operation using the OpenClaw and Paperclip systems to automate global attacks...

CVE-2026-42430

OpenClaw before 2026.4.8 contains a server-side request forgery vulnerability in Playwright redirect handling that allows attackers to bypass strict SSRF checks. Attackers can exploit request-time navigation to reach private targets that should be restricted by browser SSRF protections...

CVE-2026-41914

OpenClaw before 2026.4.8 contains a server-side request forgery vulnerability in QQ Bot media download paths that bypass SSRF protection. Attackers can exploit unprotected media fetch endpoints to access internal resources and bypass allowlist policies...

CVE-2026-42423

OpenClaw before 2026.4.8 contains an approval-timeout fallback mechanism that bypasses strictInlineEval explicit-approval requirements on gateway and node exec hosts. Attackers can exploit this timeout fallback to execute inline eval commands that should require explicit user approval,...

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw As a Case Study

Autonomous agent frameworks built upon large language models LLMs are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and...

@agentholdings/agent-passport (>=0.1.0, <=0.1.5), @chrysb/alphaclaw (>=0.8.3-beta.1, <=0.9.5) +21 more potentially affected by CVE-2026-44996 via openclaw (>=2026.3.22, <=2026.4.12)

openclaw NPM version =2026.3.22, =0.1.0, =0.8.3-beta.1, =0.1.0, =2026.3.25, =27.2.5, =1.1.0, =2.1.3, =2026.3.24-3, =0.14.39, =0.1.0, =0.1.1, =0.2.18 - @xmoxmo/bncr 0.0.8 - morpho-vault-manager 0.1.0 and more Source cves: CVE-2026-44996 Source advisory: OSV:GHSA-GFG9-5357-HV4C...

@agentholdings/agent-passport (>=0.1.0, <=0.1.5), @chrysb/alphaclaw (>=0.8.3-beta.1, <=0.9.5) +21 more potentially affected by CVE-2026-44996 via openclaw (>=2026.3.22, <=2026.4.12)

openclaw NPM version =2026.3.22, =0.1.0, =0.8.3-beta.1, =0.1.0, =2026.3.25, =27.2.5, =1.1.0, =2.1.3, =2026.3.24-3, =0.14.39, =0.1.0, =0.1.1, =0.2.18 - @xmoxmo/bncr 0.0.8 - morpho-vault-manager 0.1.0 and more Source cves: CVE-2026-44996 Source advisory: SNYK:JS-OPENCLAW-16322612...

OpenClaw: Webchat audio embedding could read local files without local-root containment

Impact OpenClaw deployments before 2026.4.15 could embed host-local audio files into webchat responses without applying the local media root containment check used by other media-serving paths. If an attacker could influence an agent or tool-produced ReplyPayload.mediaUrl, the webchat audio...

GHSA-GFG9-5357-HV4C OpenClaw: Webchat audio embedding could read local files without local-root containment

Impact OpenClaw deployments before 2026.4.15 could embed host-local audio files into webchat responses without applying the local media root containment check used by other media-serving paths. If an attacker could influence an agent or tool-produced ReplyPayload.mediaUrl, the webchat audio...

@agentholdings/agent-passport (>=0.1.0, <=0.1.5), @chrysb/alphaclaw (>=0.8.3-beta.1, <=0.9.5) +21 more potentially affected by CVE-2026-44991 via openclaw (>=2026.3.22, <=2026.4.12)

openclaw NPM version =2026.3.22, =0.1.0, =0.8.3-beta.1, =0.1.0, =2026.3.25, =27.2.5, =1.1.0, =2.1.3, =2026.3.24-3, =0.14.39, =0.1.0, =0.1.1, =0.2.18 - @xmoxmo/bncr 0.0.8 - morpho-vault-manager 0.1.0 and more Source cves: CVE-2026-44991 Source advisory: OSV:GHSA-C28G-VH7M-FM7V...