VulnSocial

CVE-2026-57123Disclosure

LOWCVSS 9.8 · CRITICAL

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, ToolsMCPServer.run_sse and launch_tools_mcp_server bind to 0.0.0.0 and create /sse and /messages/ routes without invoking the available SecurityConfig authentication, origin-validation, or DNS-rebinding controls. Any reachable client can list and invoke registered tools, and a browser can target a local instance through DNS rebinding, with impact determined by the registered file, shell, and code-execution tools. This vulnerability is fixed in praisonaiagents 1.6.59.

Back to dashboard
0.0/ 10 priority

Sources & remediation

Other references
Weakness type (CWE)
CWE-306CWE-350CWE-1327

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

STABLE

Threat summary

  • 3 mentions across 2 observed days
  • Momentum state: stable

What's happening

  • Technical details provided in 3 signals
  • Disclosure: 3 classified signals
  • Peaked 1d ago at 2 mentions (2026-09-15); latest day: 1
  • 3 total mentions across 2 days

Deep dive

Activity timeline3 mentions / 2d
01122Mentions · 2026-09-15: 2Mentions · 2026-09-16: 1Technical Details · 2026-09-15: 2Technical Details · 2026-09-16: 109-1509-16
Signal classification1 categories
Disclosure
3100.0%
Referenced assets2 URLs
Classification over time
DateTotalLabels
2026-09-152
Disclosure2
2026-09-161
Disclosure1
Full discourse3 posts
  • Ryx@PadhiyarRushi
    Disclosure

    PraisonAI / praisonaiagents stack hit with five separate CVSS 9.8 remote code execution CVEs in a single disclosure window (CVE-2026-57123 through related IDs). AI agent frameworks that accept and execute untrusted tool or workflow input keep producing the same pattern: missing auth, missing isolation, full RCE. Developer tooling that becomes production infrastructure needs production security. https://cvebrief.com/ #Cybersecurity #AI #AISecurity #MCP #Claude #GPT #Infosec #Trending #AgentSecurity #RCE

    Post summary

    The post announces multiple critical remote code execution CVEs affecting the PraisonAI / praisonaiagents stack and describes the underlying vulnerability pattern, but does not provide exploitation details, active exploitation claims, or remediation steps.

    32140296
    954 followersView on X
  • Cybersecurity News DE@cybsecuritynews
    Disclosure

    Update: PraisonAI: Zwei kritische Lücken erlauben Remote-Code-Ausführung ohne Anmeldung https://cybersecurity-news.de/praisonai-kritische-schwachstellen-cve-2026-57123-cve-2026-57125

    Post summary

    The post announces two critical CVEs affecting PraisonAI (CVE-2026-57123 and CVE-2026-57125) that enable unauthenticated remote code execution, linking to a news article for further details, without mentioning any exploit tools, active exploitation, patches, or PoC code.

    0001042
    12 followersView on X
  • Cybersecurity News DE@cybsecuritynews
    Disclosure

    #schwachstellen PraisonAI: Zwei kritische Lücken erlauben Remote-Code-Ausführung ohne Anmeldung #cve202657123 #cve202657125 #praisonai #praisonaiagents https://cybersecurity-news.de/praisonai-kritische-schwachstellen-cve-2026-57123-cve-2026-57125

    Post summary

    The tweet discloses two critical CVEs (CVE-2026-57123, CVE-2026-57125) in PraisonAI that enable unauthenticated remote code execution, directing readers to a news article for further details.

    0000034
    12 followersView on X

Explore more

Back to dashboard