Xalgorix Autonomous AI Pentesting Agent 4.6.99

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

PT-2026-99184

Name of the Vulnerable Software and Affected Versions OpenClaw versions 2026.7.1 through 2026.7.2 Description OpenClaw, distributed as the npm package openclaw, contains an issue where alternate but valid file: URL spellings supplied over the Agent Client Protocol ACP are treated as relative path...

CVE-2026-100547: Incorrect Behavior Order: Validate Before Canonicalize

OpenClaw is a coding agent distributed as the npm package openclaw. In affected versions 2026.7.1 through 2026.7.2, alternate but valid file: URL spellings supplied over the Agent Client Protocol ACP were treated as relative paths and were incorrectly classified as reads scoped to the session...

CVE-2026-100535: Incorrect Authorization

OpenClaw npm package 'openclaw' versions = 2026.4.5 and 2026.8.1 can lose the originating requester's restrictions and untrusted provenance when session-derived text is persisted to session memory. In deployments where session-memory capture and dreaming are enabled, a restricted external sender...

CVE-2026-100575: Missing Authorization

OpenClaw Slack versions before 2026.8.1 fail to properly enforce sender allowlists in multi-person direct messages. Disallowed participants can trigger Slack agents and access tools and data granted to those agents by bypassing configured sender policies...

ORBIT: A Framework for Multi-Agent Safety and Security Evaluations

Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to significant safety and security risks: the flexible protocols that enable task generalization also expose novel threats, fr...

PT-2026-99425

Name of the Vulnerable Software and Affected Versions Kibana affected versions not specified Description A Confused Deputy issue in Kibana Agent Builder allows a non-administrative user with permissions to edit a shared agent to trigger privileged operations. These operations are executed using t...

CVE-2026-100591: Missing Authorization

OpenClaw is an npm-distributed agent gateway. In versions before 2026.7.1, the global Active Memory toggle mutations could omit owner checks. An authorized non-owner external-channel sender could therefore persistently enable or disable Active Memory for the Gateway, disabling memory recall for...

CVE-2026-63006

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, attacker-controlled HTML in inbound emails or tickets could bypass the image URL sanitizer using path traversal sequences. When an authenticated agent views the content, the browser resolves the URL to a protected...

CVE-2026-63006

Prior to version 7.1.2 , the Zammad helpdesk system is vulnerable to a security bypass where attacker-controlled HTML in inbound emails or tickets can circumvent the image URL sanitizer . By using path traversal sequences , an attacker can cause the browser to resolve a URL to a protected API end...

CVE-2026-63006 Zammad: HTML sanitizer API path allowlist bypass via interior path traversal in img src/srcset

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, attacker-controlled HTML in inbound emails or tickets could bypass the image URL sanitizer using path traversal sequences. When an authenticated agent views the content, the browser resolves the URL to a protected...

EUVD-2026-87270

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, attacker-controlled HTML in inbound emails or tickets could bypass the image URL sanitizer using path traversal sequences. When an authenticated agent views the content, the browser resolves the URL to a protected...

CVE-2026-63006 Zammad: HTML sanitizer API path allowlist bypass via interior path traversal in img src/srcset

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, attacker-controlled HTML in inbound emails or tickets could bypass the image URL sanitizer using path traversal sequences. When an authenticated agent views the content, the browser resolves the URL to a protected...

CVE-2026-63204 Zammad: Authenticated agents can read AI summary error messages from inaccessible tickets

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, an authenticated user with agent permissions can supply an arbitrary AI analytics run identifier to the ticket summarize endpoint and receive the AI provider error message stored for that run, even if the run...

CVE-2026-63204 Zammad: Authenticated agents can read AI summary error messages from inaccessible tickets

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, an authenticated user with agent permissions can supply an arbitrary AI analytics run identifier to the ticket summarize endpoint and receive the AI provider error message stored for that run, even if the run...

CVE-2026-63204 Zammad: Authenticated agents can read AI summary error messages from inaccessible tickets

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, an authenticated user with agent permissions can supply an arbitrary AI analytics run identifier to the ticket summarize endpoint and receive the AI provider error message stored for that run, even if the run...

CVE-2026-84462

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, a security filter that protects Zammad's AI Agent configuration can be bypassed by entering specially crafted text into one of an AI Agent's fields. An administrator with permission to create or edit AI Agents cou...

CVE-2026-56730

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.2, an authorization bypass vulnerability was found that allows an authenticated agent to read knowledge base answer content they should not be able to access. The vulnerable GraphQL mutation is meant to transform a...

EUVD-2026-87245

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, a security filter that protects Zammad's AI Agent configuration can be bypassed by entering specially crafted text into one of an AI Agent's fields. An administrator with permission to create or edit AI Agents cou...

CVE-2026-84462 Zammad: AI Agent template sanitizer bypass leads to remote code execution

Zammad is a web based open source helpdesk/customer support system. Prior to 7.1.2, a security filter that protects Zammad's AI Agent configuration can be bypassed by entering specially crafted text into one of an AI Agent's fields. An administrator with permission to create or edit AI Agents cou...