¡Ya disponible! Investigación de Telegram 2025 — los principales insights del año 
AISecHub
Ir al canal en Telegram
Powered by InnovGuard.com | Business inquiries: https://calendly.com/innovguard/meeting | tal.eliyahu@innovguard.com
Mostrar másEl país no está especificadoTecnologías y Aplicaciones28 464
2 452
Suscriptores
+624 horas
+207 días
+14930 días
Carga de datos en curso...
Canales Similares
Sin datos
¿Algún problema? Por favor, actualice la página o contacte a nuestro gerente de soporte.
Nube de Etiquetas
Menciones Entrantes y Salientes
---
---
---
---
---
---
Atraer Suscriptores
junio '26
junio '26
+46
en 3 canales
mayo '26
+163
en 4 canales
Get PRO
abril '26
+100
en 2 canales
Get PRO
marzo '26
+192
en 3 canales
Get PRO
febrero '26
+239
en 5 canales
Get PRO
enero '26
+394
en 4 canales
Get PRO
diciembre '25
+204
en 4 canales
Get PRO
noviembre '25
+140
en 4 canales
Get PRO
octubre '25
+167
en 3 canales
Get PRO
septiembre '25
+270
en 1 canales
Get PRO
agosto '25
+95
en 1 canales
Get PRO
julio '25
+93
en 2 canales
Get PRO
junio '25
+68
en 1 canales
Get PRO
mayo '25
+375
en 3 canales
Get PRO
abril '25
+43
en 2 canales
Get PRO
marzo '25
+735
en 1 canales
| Fecha | Crecimiento de Suscriptores | Menciones | Canales | |
| 14 junio | 0 | |||
| 13 junio | +6 | |||
| 12 junio | +1 | |||
| 11 junio | +1 | |||
| 10 junio | +7 | |||
| 09 junio | +4 | |||
| 08 junio | +4 | |||
| 07 junio | +1 | |||
| 06 junio | 0 | |||
| 05 junio | +2 | |||
| 04 junio | +5 | |||
| 03 junio | +6 | |||
| 02 junio | +4 | |||
| 01 junio | +5 |
Publicaciones del Canal
| 2 | https://www.politico.com/news/2026/06/13/inside-the-whirlwind-24-hours-that-led-the-white-house-to-slap-export-controls-on-anthropic-00961519 | 105 |
| 3 |  https://github.com/OWASP/CheatSheetSeries/blob/master/cheatsheets/AI_Agent_Security_Cheat_Sheet.md | 106 |
| 4 |  Sin texto... | 97 |
| 5 |  https://x.com/ostynhyss/status/2065837960902087124 | 102 |
| 6 |  https://www.aisi.gov.uk/blog/realitytest-do-ai-systems-disclose-their-identity-when-asked | 157 |
| 7 |  Sin texto... | 235 |
| 8 | CVE-2026-47345: TYPO3 HTML Sanitizer XSS via namespace attribute encoding bug
The advisory describes an HTML serialization bug where namespace attributes aren’t encoded correctly, enabling a bypass of typo3/html-sanitizer’s XSS prevention prior to 2.3.2.
#VulnerabilityResearch #AppSec #AISecurity #Advisory
https://github.com/advisories/GHSA-p5j5-4j3q-8mq8 | 267 |
| 9 | CVE-2026-46370: Fleet observer-level enrollment secret extraction via ORDER BY oracle in labels host-listing endpoint
The advisory describes a data-exfiltration path where untrusted sorting/cursor behavior (ORDER BY) becomes an oracle, enabling a low-privilege authenticated user to binary-search and recover enrollment secrets from the labels host-listing endpoint.
#VulnerabilityResearch #AppSec #AISecurity #Advisory
https://github.com/advisories/GHSA-vxm7-9x8v-8gm4 | 243 |
| 10 |  https://www.anthropic.com/news/fable-mythos-access | 246 |
| 11 |  https://www.varonis.com/blog/openclaw-phishing | 245 |
| 12 |  https://datatracker.ietf.org/doc/draft-mohiuddin-mcp-security-considerations/ | 234 |
| 13 |  That was quick! 17 Boosts!!!
Thank you all boosting the channel.
We have now auto translate function!
https://t.me/boost/AISecHub | 247 |
| 14 |  https://github.com/bkerler/ida_rpc | 246 |
| 15 |  https://open.substack.com/pub/oliverpatel/p/the-ultimate-agentic-ai-governance | 237 |
| 16 | CVE-2026-48039: Meta Ads MCP — Unauthenticated HTTP Tool Execution Leaks Operator Meta Access Token
The advisory describes an MCP server where unauthenticated HTTP requests can trigger tool execution and expose the operator’s Meta access token, indicating a missing authn/authz boundary between remote callers and privileged MCP actions.
#MCP #AgentSecurity #AISecurity #Advisory
https://github.com/advisories/GHSA-9gw6-46qc-99vr | 259 |
| 17 | npm Supply Chain Under Siege: TeamPCP, Miasma, and npm v12
The npm package registry serves as foundational infrastructure for modern software development.
#AgentSecurity #LLMSecurity #AISecurity #Report
https://labs.cloudsecurityalliance.org/research/csa-whitepaper-npm-ai-toolchain-supply-chain-security-v1-0-c | 221 |
| 18 | OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
OCELOT treats agent privacy as trajectory-level posterior-risk control: each outbound “release” is audited and charged against a leakage budget based on how much it can improve an attacker’s belief about a secret, not just whether the text matches a filter.
#AgentSecurity #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.12341 | 199 |
| 19 | PI-Hunter: Automated Red Teaming to Expose and Localize Prompt Injections
PI-Hunter frames indirect prompt injection as an auditing problem: generate source-aware environments, then use feedback-driven test evolution to make an agent retrieve and surface latent malicious instructions, helping localize where untrusted content propagates through the agent/tool workflow.
#PromptInjection #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.12737 | 177 |
| 20 | Stakeholder-Centric Prompt Injection Benchmarking for Real-World Web Agents
This paper reframes web-agent prompt-injection evaluation around “who gets harmed,” splitting attacks by stakeholder (user/seller/platform), objective, and both outcome- and process-level metrics to surface failure modes that attack-centric benchmarks can miss.
#PromptInjection #LLMSecurity #AISecurity #Research
https://arxiv.org/abs/2606.13385 | 146 |
