Lucene search
+L

92 matches found

Kitploit
Kitploit
•added 2026/11/19 11:30 p.m.•8 views

memory-poison-lab

Memory Poisoning Lab Your agent remembered it. Should it have? A local test range for agent memory poisoning: persistent memory as an attack surface. Feed an agent's memory controlled untrusted writes, watch a planted memory change what the agent does, then try to stop it - and prove the repair...

6.2AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/17 12:25 a.m.•8 views

memform-code

MemForm evaluation release This repository accompanies the paper MemForm: Benchmarking Memory Formation Poisoning in LLM Agents. MemForm is a deterministic benchmark of persistent-memory poisoning in LLM agents. It asks a causal question that ordinary jailbreak or prompt-injection suites do not...

6.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/29 12:00 a.m.•16 views

Accept Changes, Reject Attacks: Robust Memory Management for LLM Agents

Since large language model LLM agents rely on long-term memory, what they store now shapes what they do later. A memory manager decides how each input changes this memory and which records the agent acts on. It can fail in two ways: keeping a fact that has since changed outdated memory, or storin...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/15 12:00 a.m.•35 views

GRAD: Graph-Structured Antibody Defense for LLM Agents

Memory poisoning and decomposition attacks distribute malicious evidence across the operations of large language model agents. Existing request-level defenses can miss such attacks because they assess individual inputs without connecting earlier information to later actions. Moreover, detectors...

6AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/09/14 5:23 p.m.•69 views

memory-poisoning-axis

memory-poisoning-axis Deterministic memory-poisoning / prompt-injection measurement — anchored to CVE-2026-24301 "CoSnitch" Microsoft Copilot Personal, CVSS 3.1 8.8, patched 18 Aug 2026. CoSnitch chained: i automatic prompt execution ?q= + undocumented ?autorun=1, ii data exfiltration via...

8.8CVSS8.3AI score0.01111EPSS
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/12 12:00 a.m.•13 views

When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external sources may be written into persistent memory and persist across...

5.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/08 12:00 a.m.•48 views

MemSentry: A Framework for Detecting Persistent Memory Poisoning in Agentic AI

Agentic AI systems with persistent memory introduce a distinct attack surface known as memory poisoning, in which adversarially crafted content is stored in long-term memory and subsequently influences future agent behavior. Such attacks can suppress security alerts, facilitate privilege...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/02 12:00 a.m.•62 views

CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents

Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or adversarial...

5.9AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/08/06 11:30 a.m.•30 views

AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory

A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every major AI assistant: pre-filled deep links. We observed production websites embedding hidden prompt...

5.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/08/01 12:00 a.m.•120 views

Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design introduces a security gap absent in single-agent settings: once an agent accepts adversarial content, ...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/07/29 12:00 a.m.•79 views

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasing...

5.9AI score
SaveExploits0
CVE
CVE
•added 2026/07/19 3:41 p.m.•61 views

CVE-2026-64182

The CVE-2026-64182 vulnerability concerns the Linux kernel memory subsystem: memblk_nr_poison_inc() and memblk_nr_poison_sub() look up a memory block via find_memory_block_by_id(), which returns a reference to the memory block device. Both helpers use the returned memory block without dropping th...

5.5CVSS5.5AI score0.00114EPSS
SaveExploits0References5Affected Software1
PyPA
PyPA
•added 2026/07/13 3:46 p.m.•56 views

Serena: Unauthenticated Flask dashboard on fixed port enables DNS rebinding → memory poisoning → RCE

SummarySerena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port TCP 24282, hardcoded as 0x5EDA in constants.py. The server has no authentication, no CSRF protection, and no Host header validation. A DNS rebinding attack allows a malicious webpage to reach...

8.3CVSS6.6AI score0.00373EPSS
SaveExploits1References7Affected Software1
osv_ghsa
osv_ghsa
•added 2026/07/08 9:12 p.m.•40 views

GHSA-37H2-6P4F-MP3Q Serena: Unauthenticated Flask dashboard on fixed port enables DNS rebinding → memory poisoning → RCE

Summary Serena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port TCP 24282, hardcoded as 0x5EDA in constants.py. The server has no authentication, no CSRF protection, and no Host header validation. A DNS rebinding attack allows a malicious webpage to reach...

8.3CVSS6.6AI score0.00373EPSS
SaveExploits1References5
osv_cve
osv_cve
•added 2026/07/07 8:50 p.m.•29 views

CVE-2026-49471 Serena: Unauthenticated Flask dashboard on fixed port enables DNS rebinding → memory poisoning → RCE

Serena is a powerful MCP toolkit for coding that provides semantic retrieval and editing capabilities. Prior to v1.5.2, Serena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port, with no authentication, no CSRF protection, and no Host header validation. A D...

8.3CVSS6.5AI score
SaveExploits0References5
CVE
CVE
•added 2026/07/07 8:50 p.m.•125 views

CVE-2026-49471

Serena exposes an unauthenticated Flask API on a fixed port prior to v1.5.2, with no authentication, CSRF protection, or Host header validation. A DNS rebinding attack can reach this API from any browser and write arbitrary content to the agent’s persistent memory store, which the agent may read ...

8.3CVSS6.5AI score0.00373EPSS
SaveExploits1References3Affected Software1
Cvelist
Cvelist
•added 2026/07/07 8:50 p.m.•67 views

CVE-2026-49471 Serena: Unauthenticated Flask dashboard on fixed port enables DNS rebinding → memory poisoning → RCE

Serena is a powerful MCP toolkit for coding that provides semantic retrieval and editing capabilities. Prior to v1.5.2, Serena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port, with no authentication, no CSRF protection, and no Host header validation. A D...

8.3CVSS0.00373EPSS
SaveExploits1References3
Packet Storm News
Packet Storm News
•added 2026/06/29 12:00 a.m.•69 views

Forensic Trajectory Signatures for Agent Memory Poisoning Detection

We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through observable memory-tool invocations, successful attacks require calling memoryrecallfact before emailsendemail, a transition that non-exfiltrating...

5.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/06/09 12:00 a.m.•88 views

MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents

External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However, this paradigm introduces a critical vulnerability: malicious content injected into memory can be persistently recalled and repeatedly influence age...

5.4AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
•added 2026/06/04 7:14 p.m.•50 views

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

8.8CVSS7.5AI score0.32379EPSS
SaveExploits10
Rows per page
Query Builder