CVE-2026-105135 InternLM MindSearch Planner Agent graph.py ExecutionAction.run code injection

A vulnerability has been found in InternLM MindSearch 0.1.0. This issue affects the function ExecutionAction.run of the file mindsearch/agent/graph.py of the component Planner Agent. The manipulation of the argument inputs leads to code injection. The attack can be initiated remotely. The exploit...

Xalgorix Autonomous AI Pentesting Agent 4.6.142

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...

Can CaMeLs Talk? Securing Multi-Agent Systems against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL Debenedetti et al., 2025 mitigates this threat for an individual agent by separating trusted control flow from...

CVE-2026-105135: Improper Control of Generation of Code

A vulnerability has been found in InternLM MindSearch 0.1.0. This issue affects the function ExecutionAction.run of the file mindsearch/agent/graph.py of the component Planner Agent. The manipulation of the argument inputs leads to code injection. The attack can be initiated remotely. The exploit...

Characterizing Security Effects of OSS Vulnerabilities in Agent Systems

Software agents increasingly depend on open-source components when executing tools and interacting with external systems. Security flaws in these dependencies may therefore influence more than the software process in which they occur: their consequences can be carried through tool outputs, agent...

Decepticon v1.2.2

Decepticon — Autonomous Red Team Agent "Another AI hacker? Let us guess — it runs nmap and writes a report." Commercial product demo ☁️ Don't want to self-host? Decepticon is live in the cloud. Skip the Docker setup — run autonomous red-team engagements right from your browser. Open-source CLI dem...

Muse Creates Detailed Profiles of All Your Friends and Family

Millions have downloaded Meta’s AI agent Muse. But getting it to do your bidding comes with privacy costs...

co.elastic.apm:apm-agent-attach-cli (>=1.50.0, <=1.57.1), org.opensearch:opensearch-plugin-cli (>=1.3.20, <=2.16.0) potentially affected by CVE-2026-85515 via org.bouncycastle:bcpg-fips (1.0.7.1)

org.bouncycastle:bcpg-fips MAVEN version 1.0.7.1 is affected by a known vulnerability. The following packages have a transitive dependency on org.bouncycastle:bcpg-fips and may be impacted: - co.elastic.apm:apm-agent-attach-cli =1.50.0, =1.3.20, =2.16.0 Source cves: CVE-2026-85515 Source advisory...

co.elastic.apm:apm-agent-attach-cli (>=1.50.0, <=1.57.1), org.opensearch:opensearch-plugin-cli (>=1.3.20, <=2.16.0) potentially affected by CVE-2026-85515 via org.bouncycastle:bcpg-fips (1.0.7.1)

org.bouncycastle:bcpg-fips MAVEN version 1.0.7.1 is affected by a known vulnerability. The following packages have a transitive dependency on org.bouncycastle:bcpg-fips and may be impacted: - co.elastic.apm:apm-agent-attach-cli =1.50.0, =1.3.20, =2.16.0 Source cves: CVE-2026-85515 Source advisory...

PT-2026-104485

The SupportCandy – AI Customer Support Ticket System & Live Chatbot Agent plugin for WordPress is vulnerable to time-based SQL Injection via the 'sort by' parameter in all versions up to, and including, 3.5.3 due to insufficient escaping on the user supplied parameter and lack of sufficient...

Bounded Reasoning: Cognitive Hierarchy in Human-Versus-AI Cyber Defense

Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets again...

Xalgorix Autonomous AI Pentesting Agent 4.6.139

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...

The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security

LLM-agent security has produced a dense landscape of defenses - prompt hardening, content filters, permission gates, sandboxes - yet no framework tells a deployer what a defense actually guarantees, or where that guarantee comes from. We apply Verification Autonomy Levels VAL - L0: LLM...

caprock (>=0.1.7, <=0.3.0), pbi-agent (0.14.0) potentially affected by CVE-2026-71416 via headroom-ai (>=0.25.0, <=0.31.0)

headroom-ai PYPI version =0.25.0, =0.1.7, =0.3.0 - pbi-agent 0.14.0 Source cves: CVE-2026-71416 Source advisory: GHSA-H46J-26Q3-RGGF...

caprock (>=0.1.7, <=0.3.0), pbi-agent (0.14.0) potentially affected by CVE-2026-71416 via headroom-ai (>=0.25.0, <=0.31.0)

headroom-ai PYPI version =0.25.0, =0.1.7, =0.3.0 - pbi-agent 0.14.0 Source cves: CVE-2026-71416 Source advisory: OSV:GHSA-H46J-26Q3-RGGF...

GO-2026-6615 vulnerabilities

Vulnerabilities for packages: grafana, traefik, kubescape-operator-fips, elastic-agent-fips, kubescape-server, kubescape, grafana-fips, elastic-agent, traefik-fips, kubescape-server-fips, kubescape-operator...

CVE-2026-103958

Server-side request forgery in the tool server and remote agent connection handling in Loom for AWS before 1.7.0 might allow an authenticated remote user to obtain the credentials of the application's own container role and to read responses from arbitrary internal network locations, via a crafte...

CVE-2026-103956

Missing authentication for critical function in the authentication dependency in Loom for AWS before 1.6.1 allowed remote actors to obtain super-admin authority over the agent control plane, including registering tool servers, reading stored integration credentials, and rewriting the IAM role...

CVE-2026-103958 Server-side request forgery in the tool server and remote agent connection handling in Loom for AWS

Server-side request forgery in the tool server and remote agent connection handling in Loom for AWS before 1.7.0 might allow an authenticated remote user to obtain the credentials of the application's own container role and to read responses from arbitrary internal network locations, via a crafte...

EUVD-2026-91773

Server-side request forgery in the tool server and remote agent connection handling in Loom for AWS before 1.7.0 might allow an authenticated remote user to obtain the credentials of the application's own container role and to read responses from arbitrary internal network locations, via a crafte...