CVE-2026-62676 (CVSS 7.1)

Description

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0.

Is your site exposed to CVE-2026-62676?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.1

HIGH

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N

EPSS — Exploit Prediction

0.0030

Probability of exploitation

0.22%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-184 CWE-184

References

Other References

https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c https://github.com/omnigent-ai/omnigent/pull/389 https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0 https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf

Frequently Asked Questions

What is CVE-2026-62676? +

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0. It has a CVSS v3.1 base score of 7.1 (HIGH).

How severe is CVE-2026-62676? +

CVE-2026-62676 has a CVSS v3.1 score of 7.1 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0030, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-62676? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-93598

ArcadeDB (Maven artifact com.arcadedb:arcadedb-engine) through 26.8.1 contains an incomplete deny-list in the polyglot script sandbox: com.arcadedb.query.polyglot.HostClassLookupFilter.DENIED lists java.util.ResourceBundle as a …

CVE-2026-54090

File Browser is a file managing interface for uploading, deleting, previewing, renaming, and editing files within a specified directory. Prior …

CVE-2026-126206

Loofah is a general library for manipulating and transforming HTML/XML documents and fragments, built on top of Nokogiri. In 2.25.2, …

CVE-2026-126209

Loofah is a general library for manipulating and transforming HTML/XML documents and fragments, built on top of Nokogiri. From 2.25.0 …

CVE-2026-126361

Astro is a web framework for content-driven websites. Prior to 7.4.5, Astro rendered a string used as a dynamic element …

CVE-2025-71355

Picklescan before 0.0.25 fails to detect unsafe global functions in the Numpy library, allowing attackers to bypass static analysis and …

CVE-2026-62676