Unauthorized tool execution via late approval callback
Published Sep 15, 2026 · Updated Sep 15, 2026
Incorrect authorization in PraisonAI 1.4.0 through 1.7.1 allows remote authenticated users to execute rejected tool operations. The TypeScript AgentLoop passes executable tools to generateText(), which runs handlers and fills toolResults before onToolCall evaluates approval. Exposure requires an application to accept lower-trust prompts, use onToolCall as an approval boundary, and register tools whose side effects run with the PraisonAI process's privileges.
Summary
What happened
Incorrect authorization in PraisonAI 1.4.0 through 1.7.1 allows remote authenticated users to execute rejected tool operations. The TypeScript AgentLoop passes executable tools to generateText(), which runs handlers and fills toolResults before onToolCall evaluates approval. Exposure requires an application to accept lower-trust prompts, use onToolCall as an approval boundary, and register tools whose side effects run with the PraisonAI process's privileges.
The record
- CVE
- CVE-2026-57137
- Published
- Sep 15, 2026
- Updated
- Sep 15, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-862, CWE-693, CWE-863
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Sep 15, 2026CVE publishedPublication date reported by the CVE source.
- Sep 15, 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=>= 1.4.0, < 1.7.2
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
- Deterministic AgentLoop post-execution approval proofproof 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