اکنون در دسترس! پژوهش تلگرام ۲۰۲۵ — مهمترین بینشهای سال 
AISecHub
رفتن به کانال در Telegram
Powered by InnovGuard.com | Business inquiries: https://calendly.com/innovguard/meeting | tal.eliyahu@innovguard.com
نمایش بیشترکشور مشخص نشده استفناوری و برنامهها28 584
2 446
مشترکین
+524 ساعت
+187 روز
+15130 روز
در حال بارگیری داده...
کانالهای مشابه
هیچ دادهای
مشکلی وجود دارد؟ لطفاً صفحه را تازه کنید یا با مدیر پشتیبانی ما تماس بگیرید.
ابر برچسبها
اشارات ورودی و خروجی
---
---
---
---
---
---
جذب مشترکین
ژوئن '26
ژوئن '26
+38
در 3 کانالها
مه '26
+163
در 4 کانالها
Get PRO
آوریل '26
+100
در 2 کانالها
Get PRO
مارس '26
+192
در 3 کانالها
Get PRO
فوریه '26
+239
در 5 کانالها
Get PRO
ژانویه '26
+394
در 4 کانالها
Get PRO
دسامبر '25
+204
در 4 کانالها
Get PRO
نوامبر '25
+140
در 4 کانالها
Get PRO
اکتبر '25
+167
در 3 کانالها
Get PRO
سپتامبر '25
+270
در 1 کانالها
Get PRO
اوت '25
+95
در 1 کانالها
Get PRO
ژوئیه '25
+93
در 2 کانالها
Get PRO
ژوئن '25
+68
در 1 کانالها
Get PRO
مه '25
+375
در 3 کانالها
Get PRO
آوریل '25
+43
در 2 کانالها
Get PRO
مارس '25
+735
در 1 کانالها
| تاریخ | رشد مشترکین | اشارات | کانالها | |
| 11 ژوئن | 0 | |||
| 10 ژوئن | +7 | |||
| 09 ژوئن | +4 | |||
| 08 ژوئن | +4 | |||
| 07 ژوئن | +1 | |||
| 06 ژوئن | 0 | |||
| 05 ژوئن | +2 | |||
| 04 ژوئن | +5 | |||
| 03 ژوئن | +6 | |||
| 02 ژوئن | +4 | |||
| 01 ژوئن | +5 |
پستهای کانال
| 2 |  300 followers :)
https://github.com/TalEliyahu | 113 |
| 3 |  بدون متن... | 171 |
| 4 |  https://github.com/visa/visa-vulnerability-agentic-harness | 165 |
| 5 | Top 20 Cybersecurity Talks — May 2026
https://medium.com/@taleliyahu/top-20-cybersecurity-talks-may-2026-e67929243e6f | 273 |
| 6 |  بدون متن... | 186 |
| 7 | CISA Makes Risk-Based Vulnerability Management Real
https://cyber-biz.com/blog/cisa-risk-based-vulnerability-management | 183 |
| 8 | https://socket.dev/blog/mini-shai-hulud-miasma-and-hades-worms-target-bioinformatics-and-mcp-developers-via-malicious | 183 |
| 9 |  بدون متن... | 183 |
| 10 | Help to boost it :)
I want to use few more Telegram functions.
https://t.me/boost/AISecHub | 177 |
| 11 | CVE-2026-47155: vLLM artifact pinning gaps can load unpinned code, weights, and processors
The advisory reports that vLLM revision pinning is not applied uniformly across all model artifacts, so a deployment pinned via --revision/--code-revision may still fetch and execute other dynamic components (e.g., code, weights, processors) outside the intended lock.
#VulnerabilityResearch #AppSec #AISecurity #Advisory
https://github.com/advisories/GHSA-3ww4-5jv9-j5gm | 166 |
| 12 | Turn Specs Into Evals for Agents With ASSERT
ASSERT turns natural-language behavior requirements into executable tests for models/agents, making those specs usable as regression gates to catch behavioral drift or policy violations during iteration.
#AgentSecurity #LLMSecurity #AISecurity #Blog
https://commandline.microsoft.com/assert-written-intent-executable-evals | 147 |
| 13 | Five-Plane Reference Architecture for Runtime Governance of Production AI Agents
The paper frames agent risk as stateful, delegated tool/action chains rather than single requests, and proposes “composite principals” with capability attenuation plus stop-anywhere mediation across reasoning + network/identity/endpoint/data enforcement planes to make runtime decisions and audits reconstructable.
#AgentSecurity #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.12320 | 134 |
| 14 | Agents All the Way Down: Methodology for Building Custom AI Agents from Substrate to Production
The paper frames agent security boundaries as engineering choices in the substrate and building blocks (tools/messages, function calling, MCP, orchestration), and proposes “agent-tests-agent” where a general-purpose agent runs behavioral scenarios to complement classical testing across the agent lifecycle.
#AgentSecurity #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.11869 | 129 |
| 15 | Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security
Runtime Skill Audit (RSA) targets the trust boundary where a “skill” looks benign statically but triggers harmful behavior only under specific runtime context (state, assets, multi-step tool use). It probes risk-relevant interfaces, sets up the needed execution context, and labels skills from trace evidence rather than documentation or code alone.
#AgentSecurity #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.11671 | 118 |
| 16 | Recall, Not Reasoning: How AI Coding Agents Cheat Security Benchmarks
Eval results suggest two benchmark failure modes for coding agents: unintended access to “workspace” artifacts that leak answers, and patch recall from upstream sources that turns tests into memorization rather than vulnerability-fix reasoning.
#AgentSecurity #LLMSecurity #AISecurity #Blog
https://endorlabs.com/learn/recall-not-reasoning-how-ai-coding-agents-cheat-security-benchmarks | 129 |
| 17 | CVE-2026-47751: Claude Code Action enables malicious MCP config in PRs
The advisory describes a trust-boundary break where attacker-controlled PR content can supply a .mcp.json that’s auto-discovered and then auto-enables project MCP servers (enableAllProjectMcpServers), turning repository data into tool/server configuration and exposing code execution and secret-handling paths.
#MCP #AgentSecurity #AISecurity #Advisory
https://github.com/advisories/GHSA-8q5r-mmjf-575q | 140 |
| 18 | https://t.me/boost/AISecHub | 7 |
| 19 | https://blog.cryptographyengineering.com/2026/06/09/apples-siri-ai-or-more-shouting-into-the-void-about-private-agents/ | 179 |
| 20 |  https://kasra.blog/blog/i-spent-1500-seeing-if-llms-could-hack-my-app/ | 187 |
