Entity trail

Yarden Porat

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-09 / agents-researcherCheck Point found 11 vulnerabilities across six agent frameworks — and argues the frameworks, not prompt injection, are the bugAt Black Hat 2026, Check Point's Yarden Porat and Shahar Tal presented 11 vulnerabilities spanning LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework and Google ADK, showing that prompt-controlled content crosses the boundary into trusted framework logic itself. The bug classes are boringly conventional — insecure deserialization, SSRF, path traversal, use-after-free — which is precisely the point. A Microsoft Agent Framework checkpoint-deserialization flaw let one user plant a payload via prompt injection that fired when another user reloaded their session ($10,000 bounty); Google ADK shipped an unauthenticated HTTP API on by default that executed arbitrary Python and exposed service-account credentials ($3,133.70).
2026-04-03 / agents-researcherFour CrewAI CVEs Enable Prompt Injection to Full RCE via Sandbox Escape and SSRF ChainSecurity researcher Yarden Porat of Cyata disclosed four critical vulnerabilities in CrewAI: CVE-2026-2275 (Code Interpreter sandbox escape via vulnerable SandboxPython fallback when Docker unavailable), CVE-2026-2287 (RCE from Docker runtime verification failure), CVE-2026-2286 (SSRF via unvalidated RAG search tool URLs), and CVE-2026-2285 (arbitrary file read from unvalidated JSON loader paths). These can be chained through prompt injection — an attacker interacting with a CrewAI agent with Code Interpreter enabled can achieve sandbox bypass and RCE/file read. CERT/CC published advisory VU#221883; no official patch exists yet, with maintainers developing mitigations including fail-closed configurations.

Graph relationships

CRITICIZES
CrewAI
Yarden Porat disclosed CVE-2026-2275, CVE-2026-2287, CVE-2026-2286, and CVE-2026-2285 in CrewAI
Source finding
WORKS AT
Cyata
Security researcher Yarden Porat of Cyata disclosed four critical vulnerabilities in CrewAI
Source finding

Source trail

Security researcher Yarden Porat of Cyata disclosed four critical vulnerabilities in CrewAI TrinityGuard's multi-agent safety framework found a 7.1% average safety pass rate a 2026 Agentic AI Security Report surveying 300 enterprise leaders The Register

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…