Unsafe code generation via trusted project guidance
Published Aug 6, 2026 · Updated Aug 6, 2026
Code injection in Foundation Agents MetaGPT 0.8.0 through 0.8.2 allows local users to generate unsafe code through crafted project guidance. The code-generation workflow treats supplied coding standards as authoritative and replaces parameterized SQL with attacker-influenced string interpolation. Exploitation requires control of project guidance, and the public demonstration used 1.0.0, so affected-release applicability rests on the CNA listing.
Summary
What happened
Code injection in Foundation Agents MetaGPT 0.8.0 through 0.8.2 allows local users to generate unsafe code through crafted project guidance. The code-generation workflow treats supplied coding standards as authoritative and replaces parameterized SQL with attacker-influenced string interpolation. Exploitation requires control of project guidance, and the public demonstration used 1.0.0, so affected-release applicability rests on the CNA listing.
The record
- CVE
- CVE-2026-19060
- Published
- Aug 6, 2026
- Updated
- Aug 6, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-94
- Attack vector
- local
- Privileges
- Unavailable
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=0.8.0
- Affected versionversion=0.8.1
- Affected versionversion=0.8.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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
- MetaGPT 1.0.0 code-injection 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