CVE-2026-55532
HIGH 7.6PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. This issue is fixed in version 4.6.58.
Severe if exploited (CVSS 7.6), but no known exploitation and low modeled probability. Patch on a normal cadence.
Exploitation likelihood
0.1%chance of exploitation in 30 days · 3rd percentile
Impact if exploited
7.6CVSS 3.1 · HIGH
- ConfidentialityLow
- IntegrityHigh
- AvailabilityLow
What an attacker needs
- ✓Access: Reachable over the network — no local access needed
- ✓Privileges: No account or privileges required
- ⚠User interaction: A user must take an action (click / open a file)
- ✓Complexity: No special conditions — reliably repeatable
✓ lowers the bar for an attacker · ⚠ raises it
Proof of concept & exploit code
- github-search Search GitHub for public PoC repos
Test against your own equipment
curl -s https://vulnpedia.com/cve/CVE-2026-55532/poc.jsonMachine-readable PoC index for this CVE (for automation).Listed for defensive triage, patch verification, and authorized testing on systems you own. Machine-readable: /cve/CVE-2026-55532/poc.json
Weakness (CWE)
- CWE-346: : Origin Validation Error
- CWE-352: : Cross-Site Request Forgery (CSRF)
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L
All CVSS metrics
- HIGH 7.6 v3.1 · CNA Primary
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L - HIGH 7.6 v3.1 · NVD Secondary
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L