Unauthenticated agent invocation via unguarded HTTP routes
Published Aug 25, 2026 · Updated Aug 25, 2026
Authentication bypass in PraisonAI before 4.6.58 allows remote attackers to invoke configured agents through exposed HTTP routes. The _create_agents_app() function accepts the configured API key but attaches no authentication dependency or middleware to the POST /agents routes. Exposure requires the agent server to be network-reachable; successful requests can consume model resources, return agent responses, and exercise capabilities assigned to the invoked agent.
Summary
What happened
Authentication bypass in PraisonAI before 4.6.58 allows remote attackers to invoke configured agents through exposed HTTP routes. The _create_agents_app() function accepts the configured API key but attaches no authentication dependency or middleware to the POST /agents routes. Exposure requires the agent server to be network-reachable; successful requests can consume model resources, return agent responses, and exercise capabilities assigned to the invoked agent.
The record
- CVE
- CVE-2026-55538
- Published
- Aug 25, 2026
- Updated
- Aug 25, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-306, T1190
- 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
- GHSA-r7v3-x45f-g7hp HTTP 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