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...

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 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-2026-40088

PraxionAI (PraisonAI) is vulnerable to OS command injection prior to version 4.5.121. The execute_command function and workflow shell execution accept user-controlled input through YAML workflows, agent configurations, and LLM-generated tool calls, passing commands with shell=True to subprocess.r...

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 —...

PT-2026-31717

Name of the Vulnerable Software and Affected Versions: PraisonAI versions prior to 4.5.121 Description: PraisonAI's workflow system and command execution tools are susceptible to command injection attacks because they pass user-controlled input directly to subprocess.run with shell=True. This...

CVE-2026-32898 OpenClaw < 2026.2.23 - ACP Permission Auto-Approval Bypass via Untrusted Tool Metadata

OpenClaw versions prior to 2026.2.23 contain an authorization bypass vulnerability in the ACP client that auto-approves tool calls based on untrusted toolCall.kind metadata and permissive name heuristics. Attackers can bypass interactive approval prompts for read-class operations by spoofing tool...

CVE-2026-32898

OpenClaw versions prior to 2026.2.23 contain an authorization bypass vulnerability in the ACP client that auto-approves tool calls based on untrusted toolCall.kind metadata and permissive name heuristics. Attackers can bypass interactive approval prompts for read-class operations by spoofing tool...

Explainable AI Agents: Capture LLM Tool Call Reasoning with Spring AI

When building AI agents with tool calling capabilities, developers often need insights into why an LLM chose a particular tool—not just which tool it selected. Understanding the model's reasoning process is important for debugging, observability, and building trustworthy AI systems. Spring AI now...

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

PT-2025-34260 · Unknown +1 · Qwen3 Coder +1

Name of the Vulnerable Software and Affected Versions: vLLM affected versions not specified Description: An unsafe deserialization allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. The issue...

Progent: Programmable Privilege Control for LLM Agents

LLM agents are an emerging form of AI systems where large language models LLMs serve as the central component, utilizing a diverse set of tools to complete user-assigned tasks. Despite their great potential, LLM agents pose significant security risks. When interacting with the external world, the...