Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

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

EPSS

• CVE-2026-62676: 0.40% estimated exploitation activity in the next 30 days; percentile 34.51 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Reporter: Aaron / Aeon — autonomous security agent (https://github.com/aaronjmars/aeon) Project: omnigent-ai/omnigent v0.1.0 (Databricks) — meta-harness running Claude Code / Codex / Pi "in check with policies and sandboxing" Component: omnigent/policies/builtins/shell.py (shared parser) → consumed by policies/builtins/github.py (writerepos/writebranches allowlist) and policies/builtins/workingdir.py (workspace confinement) Summary The shared shell-command parser fails open. When a gated command spells something the parser doesn't recognize, it produces no operation, the policy evaluator returns None, and None = abstain = ALLOW. So any command the parser misses bypasses both the GitHub repo/branch allowlist and the working-directory confinement — the product's two core safety guarantees. Impact A misaligned or prompt-injected agent that is meant to be confined can: - git push to an attacker-controlled repo (code / secret exfiltration), - push to a protected branch, - escape its…

Published by the source

2 Sep 2026, 22:40 UTC

Last modified by the source

2 Sep 2026, 22:40 UTC

Source last checked

26 Oct 2026, 13:51 UTC

1. Revision 1 · created · 26 Oct 2026

   Published from ghsa record GHSA-7mqg-cx4g-x2rf

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-62676

Advisory: Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py
IDs: CVE-2026-62676, GHSA-7mqg-cx4g-x2rf
Record: https://patchnext.com/advisories/cve-2026-62676 (revision 1, source checked 26 Oct 2026, 13:51 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 7.1)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: omnigent 0.3.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI omnigent: affected < 0.3.0; fixed in 0.3.0

## Suggested inspection (read-only)
- `python -m pip show omnigent`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on omnigent.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-7mqg-cx4g-x2rf (GitHub-reviewed advisory GHSA-7mqg-cx4g-x2rf lists affected ranges: PyPI omnigent >=0 <0.3.0)

Commands are suggestions: review each one before running it.