CVE-2026-64651

The CVE-2026-64651 entry concerns the @ai-sdk/harness-opencode tool that connects HarnessAgent to OpenCode via a sandboxed bridge. Before version 1.0.28, the tool would relay requests from any process whose command line included an allowed helper script path (host-tool-mcp.mjs), enabling untruste...

CVE-2026-61427 PraisonAI before 4.6.78 Authentication Bypass via HTTP-stream

PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream'...

EUVD-2026-43548

9Router through version 0.4.41 contain an unauthenticated information disclosure vulnerability that allows remote attackers to access sensitive user data by sending requests to unprotected API endpoints. Attackers can enumerate paginated request logs and retrieve complete AI conversation historie...

CVE-2026-62328 9Router 0.4.41 - Unauthenticated Information Disclosure via API Usage Endpoints

9Router through version 0.4.41 contain an unauthenticated information disclosure vulnerability that allows remote attackers to access sensitive user data by sending requests to unprotected API endpoints. Attackers can enumerate paginated request logs and retrieve complete AI conversation historie...

PYSEC-2026-2911 PraisonAI Has Unauthenticated SSE Event Stream that Exposes All Agent Activity in A2U Server

The A2U Agent-to-User event stream server in PraisonAI exposes all agent activity without authentication. This is a separate component from the gateway server fixed in CVE-2026-34952. The createa2uroutes function registers the following endpoints with NO authentication checks: - GET /a2u/info —...

PYSEC-2026-2507 ha-mcp OAuth 2.1 DCR mode enables network reconnaissance via an error oracle

Summary The ha-mcp OAuth consent form beta feature accepts a user-supplied haurl and makes a server-side HTTP request to haurl/api/config with no URL validation. An unauthenticated attacker can submit arbitrary URLs to perform internal network reconnaissance via an error oracle. Two additional co...

PYSEC-2026-2429 Composio Command Execution vulnerability

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

EUVD-2026-43181

PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem...

PYSEC-2026-1268 Composio Command Execution vulnerability

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

PYSEC-2026-461 PraisonAI Vulnerable to OS Command Injection

The executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. --- Description PraisonAI's workflow system and...

CVE-2026-50287 Missing Authentication for Critical Function in @agenticmail/mcp

AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCPHTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can...

CVE-2026-53808

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

PT-2026-48748

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.4.24 Description An authorization bypass exists in the MCP loopback feature. This allows non-owner callers to circumvent owner-only tool policies and before-tool-call hooks. When the feature is enabled and...

Malicious code in fastgrc-openclaw (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 158457237168ef50e3a6c4cd33f51e23f6aec642593745a3d11b9b4870ef36ce The package is an AI agent policy-check plugin. When a consumer does not configure their own API key, resolveApiKey returns a hardcoded BUNDLEDAPIKEY...

MAL-2026-4558 Malicious code in fastgrc-openclaw (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 158457237168ef50e3a6c4cd33f51e23f6aec642593745a3d11b9b4870ef36ce The package is an AI agent policy-check plugin. When a consumer does not configure their own API key, resolveApiKey returns a hardcoded BUNDLEDAPIKEY...

Hallucination As Exploit: Evidence-Carrying Multimodal Agents

Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or transfer, hallucination becomes an authorization failure rather than an answer-quality error. We formalize this failure mode as hallucination-to-actio...

CVE-2026-43992

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

EUVD-2026-29541

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

CVE-2026-43992 JunoClaw: MCP write tools exposed raw BIP-39 mnemonic as a tool-call parameter

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

CVE-2026-43992

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...