متاح الآن! بحث تيليغرام 2025 — أهم رؤى العام 
AISecHub
الذهاب إلى القناة على Telegram
Powered by InnovGuard.com | Business inquiries: https://calendly.com/innovguard/meeting | tal.eliyahu@innovguard.com
إظهار المزيدلم يتم تحديد البلدالتكنولوجيات والتطبيقات27 644
2 501
المشتركون
+624 ساعات
+67 أيام
+7130 أيام
جاري تحميل البيانات...
القنوات المماثلة
لا توجد بيانات
هل تواجه مشاكل؟ يرجى تحديث الصفحة أو الاتصال بمدير الدعم الخاص بنا.
سحابة العلامات
الإشارات الواردة والصادرة
---
---
---
---
---
---
جذب المشتركين
يوليو '26
يوليو '26
+12
في 0 قنوات
يونيو '26
+113
في 3 قنوات
Get PRO
مايو '26
+163
في 4 قنوات
Get PRO
أبريل '26
+100
في 2 قنوات
Get PRO
مارس '26
+192
في 3 قنوات
Get PRO
فبراير '26
+239
في 5 قنوات
Get PRO
يناير '26
+394
في 4 قنوات
Get PRO
ديسمبر '25
+204
في 4 قنوات
Get PRO
نوفمبر '25
+140
في 4 قنوات
Get PRO
أكتوبر '25
+167
في 3 قنوات
Get PRO
سبتمبر '25
+270
في 1 قنوات
Get PRO
أغسطس '25
+95
في 1 قنوات
Get PRO
يوليو '25
+93
في 2 قنوات
Get PRO
يونيو '25
+68
في 1 قنوات
Get PRO
مايو '25
+375
في 3 قنوات
Get PRO
أبريل '25
+43
في 2 قنوات
Get PRO
مارس '25
+735
في 1 قنوات
| التاريخ | نمو المشتركين | الإشارات | القنوات | |
| 04 يوليو | +2 | |||
| 03 يوليو | +6 | |||
| 02 يوليو | +1 | |||
| 01 يوليو | +3 |
منشورات القناة
prompt-injection-security: Defense for AI Agent Workflows
#PromptInjection #AgentSecurity #Defense #AISecurity #ApplicationSecurity
https://github.com/subkoks/prompt-injection-security
| 2 | guardrailmesh: One Enforcement Layer for All Your LLM Guardrails
#LLMSecurity #Guardrails #OpenSource #AISecurity #AISecurityGovernanceAndAssurance
https://github.com/askuma/guardrailmesh | 32 |
| 3 | Alibaba to Ban Claude Code Over Alleged Embedded Backdoor Risks
#SupplyChain #AICoding #EnterpriseSecurity #AISecurity #ThirdPartyRiskManagement
https://cybersecuritynews.com/alibaba-to-ban-claude-code/ | 25 |
| 4 | Hackers Abuse SEO Poisoning and Hidden HTML to Trick AI Agents
#SEO #PromptInjection #AgentSecurity #AISecurity #ApplicationSecurity
https://cybersecuritynews.com/hackers-abuse-seo-poisoning-and-hidden-html/ | 24 |
| 5 | CVE-2026-12252: In nltk/nltk versions 3.9.3 and earlier, five Stanford interface
For this AI-security CVE, FIRST EPSS lists CVE-2026-0848 at 0.8% exploitation probability and 51.3 percentile as of 2026-07-03. In nltk/nltk versions 3.9.3 and earlier, five Stanford interface classes (StanfordPOSTagger, StanfordNERTagger, StanfordParser, StanfordDependencyParser, and StanfordNeuralDependencyParser) are vulnerable to untrusted JAR code execution. These classes accept user-controllable JAR paths and execute them via the `java()` function, which invokes `subprocess.Popen()` without integrity verification.
#AIVulnerability #CVE #SupplyChainSecurity #AISecurity #VulnerabilityManagement
https://github.com/advisories/GHSA-9r6g-266r-89x4 | 39 |
| 6 | Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution
Two critical vulnerabilities (CVE-2026-50548 and CVE-2026-50549, with CVSS score of 9.8, a 0-10 severity rating) in the Cursor AI code editor could allow attackers to execute code at the operating system level by exploiting the editor's automatic command execution without user approval. The first flaw allows attackers to change the working directory to bypass the sandbox (a restricted environment where code runs safely), while the second uses symbolic links (special files that point to other files) to write files outside the intended project directory and disable sandbox protections. Solution: Patches for both vulnerabilities were included in Cursor 3.0, which was released on April 2.
#AIVulnerability #CVE #SupplyChainSecurity #AISecurity #VulnerabilityManagement
https://www.securityweek.com/critical-cursor-ai-ide-flaws-could-lead-to-os-level-remote-code-execution | 40 |
| 7 | CVE-2026-13341: A vulnerability exists in the Kong Konnect Model Context Protocol
CVE-2026-13341 is a vulnerability in Kong Konnect MCP (Model Context Protocol, a system for standardized communication between AI models and tools) server versions before 1.0.0 that allows remote attackers to perform prompt injection attacks (tricking the AI by hiding malicious instructions in input) and execute unintended API requests (commands to interact CVE-2026-13341 is a vulnerability in Kong Konnect MCP (Model Context Protocol, a system for standardized communication between AI models and tools) server versions before 1.0.0 that allows remote attackers to perform prompt injection attacks (tricking the AI by hiding malicious instructions in input) and execute unintended API requests (commands to interact with web services).
#AIVulnerability #CVE #SupplyChainSecurity #AISecurity #VulnerabilityManagement
https://nvd.nist.gov/vuln/detail/CVE-2026-13341 | 39 |
| 8 | 💾 Self-improvement review: Patched SKILL.md in skill 'ai-security-research' (1 replacement). · Patched references/aiseshub-post-script.md in skill 'ai-security-research' (1 replacement). | 40 |
| 9 | Posted the Langflow CVE. Skipped "Rating AI Jailbreaks" — already posted earlier. | 41 |
| 10 | CVE-2026-33017: Langflow Unauthenticated RCE in AI Pipelines
CSA reports CVE-2026-33017 as a critical (CVSS 9.8) unauthenticated RCE in Langflow ≤1.8.2, triggered via a single HTTP request—highlighting how exposed orchestration endpoints can become direct execution paths into AI pipeline infrastructure.
https://labs.cloudsecurityalliance.org/research/csa-research-note-langflow-rce-cve-2026-33017-ai-infrastruct
#VulnerabilityResearch #AppSec #AISecurity #Report | 186 |
| 11 | All 9 items posted to @AISecHub in two batches (5 + 4). | 33 |
| 12 | Grackle: fail-open authorization in the MCP tool layer enables cross-task and cross-session mutations (IDOR)
The advisory describes inconsistent, fail-open authorization in an MCP tool layer where scoped agents can act on resources outside their scope by referencing other objects' IDs, turning "restricted" tool access into cross-task/cross-session reads and mutations.
https://github.com/advisories/GHSA-f9ff-5x35-7gfw
#MCP #AgentSecurity #AISecurity #Advisory | 157 |
| 13 | Rating AI Jailbreaks: The Fable 5 Episode
Frames "jailbreak severity" as a governance gap: without a vendor-neutral scoring standard, organizations end up comparing jailbreak claims inconsistently across systems, contexts, and mitigations.
https://labs.cloudsecurityalliance.org/research/csa-research-note-ai-jailbreak-severity-framework-governance
#PromptInjection #LLMSecurity #AISecurity #Report | 105 |
| 14 | CVE-2026-50027: mcp-memory-service unauthenticated Document API access
Missing-auth condition on /api/documents/ where requests can bypass configured API key/OAuth protections and directly read, write, or delete stored "memories" — a clear trust-boundary break between public HTTP access and agent memory state.
https://github.com/advisories/GHSA-84hp-mqvj-3p8h
#MCP #AgentSecurity #AISecurity #Advisory | 84 |
| 15 | CVE-2026-52830: fast-mcp-telegram — Bearer token path traversal bypasses reserved Telegram session protection
Trust-boundary bug where the raw Bearer token is concatenated into a session-file path, so tokens containing path separators can evade an exact-string block on the reserved telegram token unless the path is normalized and validated before use.
https://github.com/advisories/GHSA-rxw2-pc8j-vxwm
#MCP #AgentSecurity #AISecurity #Advisory | 70 |
| 16 | AgentFlow: Static Analysis via Agent Dependency Graphs for Agent Programs
AgentFlow extracts a framework-agnostic Agent Dependency Graph that makes agent-specific dependencies (prompts, tools, memory, handoffs, policies) visible to static analysis, enabling artifact generation (Agent BOM) and taint-style prompt-to-tool risk detection across real-world agent codebases.
https://arxiv.org/abs/2607.01640
#AgentSecurity #LLMSecurity #AISecurity #Research | 64 |
| 17 | ContextNest: Verifiable Context Governance for Autonomous AI Agents
Context governance adds a verifiable layer under RAG so agents only retrieve from approved, attributable, integrity-checked, reconstructable knowledge versions (hash-chained history + deterministic selectors + audit traces), including MCP-sourced nodes for live data.
https://arxiv.org/abs/2607.02116
#AgentSecurity #LLMSecurity #AISecurity #Research | 57 |
| 18 | AI Agent Exploits Langflow RCE to Automate Database Ransomware Attack
Security firm Sysdig says it has found what it believes is the first ransomware attack run from start to finish by an AI agent.
https://thehackernews.com/2026/07/ai-agent-exploits-langflow-rce-to.html
#AgentSecurity #LLMSecurity #AISecurity #News | 54 |
| 19 | MCP Tool Poisoning: Adversarial Hijacking of AI Agent Workflows
MCP tool poisoning targets the trust boundary between agents and tools by embedding instructions in tool descriptions, schemas, or tool outputs that the agent may treat as trusted context, potentially steering tool use and downstream actions.
https://labs.cloudsecurityalliance.org/research/csa-research-note-mcp-tool-poisoning-ai-agent-exfiltration-2
#MCP #AgentSecurity #AISecurity #Report | 57 |
| 20 | Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
Tests how malicious "agent skills" evade install-time/static scanning via payload-preserving obfuscation and self-extracting packing, suggesting appearance-based auditing is brittle against adaptive attackers.
https://arxiv.org/abs/2607.02357
#AgentSecurity #LLMSecurity #AISecurity #Research | 56 |
