Unauthenticated agent execution via permission-bypassing message route
Published Aug 6, 2026 · Updated Aug 6, 2026
Missing authorization in TinyAGI 0.0.20 allows remote attackers to invoke agents through the Message API without authentication. The unauthenticated POST /api/message route queues attacker-controlled text, and processMessage sends it to Claude with --dangerously-skip-permissions. Network access to the API is sufficient; resulting tool actions are bounded by the files, commands, plugins, and internal resources available to the agent host.
Summary
What happened
Missing authorization in TinyAGI 0.0.20 allows remote attackers to invoke agents through the Message API without authentication. The unauthenticated POST /api/message route queues attacker-controlled text, and processMessage sends it to Claude with --dangerously-skip-permissions. Network access to the API is sufficient; resulting tool actions are bounded by the files, commands, plugins, and internal resources available to the agent host.
The record
- CVE
- CVE-2026-19010
- Published
- Aug 6, 2026
- Updated
- Aug 6, 2026
- Vendor
- TinyAGI
- Product
- TinyAGI
- Classifications
- CWE-863, CWE-862, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 6, 2026CVE publishedPublication date reported by the CVE source.
- Aug 6, 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=0.0.20
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
- Upstream issue 284 integration 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