PT-2026-79890

Authorization Bypass Through User-Controlled Key CWE-639 in Kibana can lead to unauthorized query execution against Elastic Agents that are assigned to a Kibana space the requesting user has no access to, via Accessing Functionality Not Properly Constrained by ACLs CAPEC-1. A user who is authoriz...

CVE-2026-75625 Kraken Agents Peer-to-Peer Download Cache Poisoning via Digest Verification Bypass

Kraken agents fail to verify peer-to-peer downloaded blobs against their requested SHA-256 digest before committing to the content-addressable cache, relying only on CRC32 checksums for piece validation. Attackers on the agent-to-agent path or malicious peers can supply substituted content with...

CVE-2026-75625

Uber Kraken's P2P blob download path skips SHA-256 digest verification before committing to the content-addressable cache, relying only on CRC32. Attackers can forge CRC32 values to inject malicious container image layers or manifests that propagate to other hosts, enabling supply-chain compromis...

CVE-2026-75625 Kraken Agents Peer-to-Peer Download Cache Poisoning via Digest Verification Bypass

Kraken agents fail to verify peer-to-peer downloaded blobs against their requested SHA-256 digest before committing to the content-addressable cache, relying only on CRC32 checksums for piece validation. Attackers on the agent-to-agent path or malicious peers can supply substituted content with...

CVE-2026-75625 Kraken Agents Peer-to-Peer Download Cache Poisoning via Digest Verification Bypass

Kraken agents fail to verify peer-to-peer downloaded blobs against their requested SHA-256 digest before committing to the content-addressable cache, relying only on CRC32 checksums for piece validation. Attackers on the agent-to-agent path or malicious peers can supply substituted content with...

MobileWorldSafety: Benchmarking GUI Agent Safety against Environmental Injection Attacks in Android Apps

LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental content, they are highly vulnerable to environmental injection attacks, which...

Benchmarking Automated Security Patch Backporting: How Far Are We?

Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets. However, these evaluations are often confined to homogeneous environments, such as one repository or specific project versions...

EUVD-2026-39104

chrome-devtools-mcp: validatePath does not canonicalize symlinks before enforcing roots...

atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard

estimatebatchcost atomicagents/agent.py looks up the per-model output price with PRICING.getmodel, , returning 0.0 for any model not in the hardcoded pricing table. checkbatchreservation then early-returns when the reservation is 0 and that an over-cap unknown-model batch raises...

GHSA-J659-8XH6-5PQ5 atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard

estimatebatchcost atomicagents/agent.py looks up the per-model output price with PRICING.getmodel, , returning 0.0 for any model not in the hardcoded pricing table. checkbatchreservation then early-returns when the reservation is 0 and that an over-cap unknown-model batch raises...

Allocation of Resources Without Limits or Throttling

Overview atomic-agents-stack is a Spec + reference implementation for vault-native, multi-runtime AI agents Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling due to improper handling of unknown models in the PRICING lookup within the...

atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

GHSA-XHCR-CQFR-M3HV atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

Resources Downloaded over Insecure Protocol

Overview atomic-agents-stack is a Spec + reference implementation for vault-native, multi-runtime AI agents Affected versions of this package are vulnerable to Resources Downloaded over Insecure Protocol via the makehttpmcpserverregistrybackendfromurl process. An attacker can execute arbitrary...

yolobox v0.19.0

root@kitploit: ██╗ ██╗ ██████╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔═══██╗╚██╗██╔╝ ╚████╔╝ ██║ ██║██║ ██║ ██║██████╔╝██║ ██║ ╚███╔╝ ╚██╔╝ ██║ ██║██║ ██║ ██║██╔══██╗██║ ██║ ██╔██╗ ██║ ╚██████╔╝███████╗╚██████╔╝██████╔╝╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═════╝ ╚══════╝...

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection,...

PT-2026-92101

Name of the Vulnerable Software and Affected Versions atomic-agents-stack versions prior to 1.1.0 Description A cost-guardrail bypass exists in the estimate batch cost function within atomic agents/agent.py. The function uses PRICING.getmodel, to look up per-model output prices, which returns a...

Beyond Direct Access: Resource Hijacking in LLM Agents

Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions...

cynative v1.9.2

Build your own security agents Open-source framework for security agents with live, read-only access to your infrastructure. Quickstart · Your first agent · Docs Ask your infrastructure anything. Cynative runs frontier models across your code, cloud and runtime - reasoning through GitHub, GitLab,...

CVE-2026-72666

Authorization Bypass Through User-Controlled Key CWE-639 in Kibana can lead to unauthorized query execution against Elastic Agents that are assigned to a Kibana space the requesting user has no access to, via Accessing Functionality Not Properly Constrained by ACLs CAPEC-1. A user who is authoriz...