Persistent prompt injection via origin prefix matching
Published Aug 25, 2026 · Updated Aug 25, 2026
Origin validation error in PraisonAI before 4.6.58 allows remote attackers to write persistent agent instructions via a malicious webpage. The MCP HTTP Stream _validate_origin method accepts any Origin beginning with a localhost allowlist entry, then parses text/plain JSON and dispatches tools/call without an API key or session. Exploitation requires a developer to run the local server without an API key and visit an attacker-controlled page; forged rule files then affect later agent runs.
Summary
What happened
Origin validation error in PraisonAI before 4.6.58 allows remote attackers to write persistent agent instructions via a malicious webpage. The MCP HTTP Stream _validate_origin method accepts any Origin beginning with a localhost allowlist entry, then parses text/plain JSON and dispatches tools/call without an API key or session. Exploitation requires a developer to run the local server without an API key and visit an attacker-controlled page; forged rule files then affect later agent runs.
The record
- CVE
- CVE-2026-55532
- Published
- Aug 25, 2026
- Updated
- Aug 25, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-346, CWE-352, T1189
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 25, 2026CVE publishedPublication date reported by the CVE source.
- Aug 25, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 4.6.58
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Browser CSRF and curl proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo