Local HTTP disclosure via automatic URL mention fetch
Published Jul 21, 2026 · Updated Jul 21, 2026
Local SSRF in PraisonAI before 4.6.40 and praisonaiagents before 1.6.40 allows attackers to read local HTTP resources through crafted CLI prompts. MentionsParser.process expands @url mentions by passing attacker-controlled HTTP URLs directly to urllib.request.urlopen, then prepends each response body to model context. Exploitation requires attacker-influenced prompt text and an operator to run the direct-prompt CLI; the demonstrated consequence is disclosure of localhost-only content.
Summary
What happened
Local SSRF in PraisonAI before 4.6.40 and praisonaiagents before 1.6.40 allows attackers to read local HTTP resources through crafted CLI prompts. MentionsParser.process expands @url mentions by passing attacker-controlled HTTP URLs directly to urllib.request.urlopen, then prepends each response body to model context. Exploitation requires attacker-influenced prompt text and an operator to run the direct-prompt CLI; the demonstrated consequence is disclosure of localhost-only content.
The record
- CVE
- CVE-2026-47395
- Published
- Jul 21, 2026
- Updated
- Jul 21, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-200, T1005
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 21, 2026CVE publishedPublication date reported by the CVE source.
- Jul 21, 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=< 4.6.40
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
- PraisonAI URL-mention loopback-fetch PoCproof 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