Credential disclosure via tool-name-only approval caching
Published Jun 18, 2026 · Updated Jun 18, 2026
Authorization bypass in PraisonAI Agents before 1.5.128 allows attackers to execute later shell commands without renewed approval. The require_approval decorator queries a ContextVar cache by tool name alone, while mark_approved stores only execute_command rather than its invocation arguments. After a user approves one benign command, an agent or prompt injection can run different commands in the same execution context and read process credentials passed to subprocesses.
Summary
What happened
Authorization bypass in PraisonAI Agents before 1.5.128 allows attackers to execute later shell commands without renewed approval. The require_approval decorator queries a ContextVar cache by tool name alone, while mark_approved stores only execute_command rather than its invocation arguments. After a user approves one benign command, an agent or prompt injection can run different commands in the same execution context and read process credentials passed to subprocesses.
The record
- CVE
- CVE-2026-56074
- Published
- Jun 18, 2026
- Updated
- Jun 18, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-863, T1059
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 18, 2026CVE publishedPublication date reported by the CVE source.
- Jun 18, 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=0 <1.5.128
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.
Public exploit references
- Approval-cache bypass proof of conceptproof of concept · unverified
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