1655 matches found
The Surprising Effectiveness of LLMs in BGP Security: Mining an Unprecedented Amount of Incidents and Boosting Anomaly Detection
Border Gateway Protocol BGP security is critical to Internet infrastructure, yet progress in routing anomaly detection has been limited by the scarcity of publicly available incident datasets, which contain only 18 recorded cases. We observe that public operator mailing lists, e.g., NANOG and...
InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires onl...
CodeMechanic: Bug-Property-Guided Program Mitigation
Automated testing discovers vulnerabilities faster than developers can investigate and repair them, leaving an interval in which known memory corruptions remain exploitable. End- to-end LLM repair agents can shorten this interval, but they synthesize open-ended code changes and commonly validate...
attackgen v0.16.0
AttackGen AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK and ATLAS frameworks. The tool generates tailored incident response scenarios based on user-selected threat actor groups, AI attack case...
BUG-BOUNTY-SLM
š”ļø Bug Bounty SLM A web front end for your existing NVIDIA-SL...
SkillBloat: Token Amplification Attacks Via Skill Injection in LLM Coding Agents
Agent skills extend coding agents with task-specific instructions, scripts, and resources, but they also create a trusted instruction channel that can be abused beyond conventional security attacks. This paper studies token amplification through skill injection: an economic resource-abuse threat ...
CVE-2026-61539
Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...
CVE-2026-54457 TensorZero: Arbitrary file read and SSRF in TensorZero Gateway's internal object storage endpoint
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation. Prior to 2026.6.0, the TensorZero Gateway /internal/objectstorage endpoint accepts a caller-supplied JSON storagepath parameter that dynamically overrides the...
dsh2shell
dsh2shell Unauthenticated RCE PoC for expo...
CVE-2026-77775
Headroom's LLM proxy lets a client choose the upstream destination with the x-headroom-base-url request header. resolveopenaiupstreambase in headroom/proxy/handlers/openai.py accepts the header value, requires only that it parse with an http or https scheme and a hostname, and returns it for use ...
CVE-2026-77776
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
CVE-2026-77776
Headroom LLM proxy (v0.29.0 and earlier) trusts the client-supplied x-headroom-user-id header as an authenticated identity without binding it to the caller. The header is read directly in headroom/proxy/handlers/openai.py across chat completion and websocket paths, allowing any client to imperson...
CVE-2026-77776 Headroom Proxy Treats the Client-Supplied x-headroom-user-id Header as an Authenticated Identity
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
EUVD-2026-63905
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
CVE-2026-77776
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
CVE-2026-77776 Headroom Proxy Treats the Client-Supplied x-headroom-user-id Header as an Authenticated Identity
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
CVE-2026-77776 Headroom Proxy Treats the Client-Supplied x-headroom-user-id Header as an Authenticated Identity
Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...
CVE-2026-77775
Headroom's LLM proxy lets a client choose the upstream destination with the x-headroom-base-url request header. resolveopenaiupstreambase in headroom/proxy/handlers/openai.py accepts the header value, requires only that it parse with an http or https scheme and a hostname, and returns it for use ...
Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making
Large language models LLMs are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived...
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
As large language model LLM agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is...