CVE Intelligence
High

CVE-2026-62676 — Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py

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.

Published Aug 21, 2026 · Updated Oct 14, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.4% (30-day exploitation probability)+5
  • Technical severity (high)+6

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.4%
ahead of 33% of scored CVEs · Oct 14, 2026
Affects
Omnigent-ai
Omnigent
CVSS base
7.1
High · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
None
none · proof-of-concept · active
Automatable
No
can an attacker script the kill-chain steps
Technical impact
Partial
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Pip Omnigent: fixed in version 0.3.0 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Omnigent-ai Omnigent, Pip Omnigent).
  2. Apply the fixed version or the patch documented under Remediation.
  3. Search available logs for exploit probes, errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Omnigent-ai Omnigent version < 0.3.0 Vulnerable CVE Program (cve.org) e CISA ADP
Pip Omnigent < 0.3.0 Vulnerable GitHub Security Advisories

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
Low
Availability
None

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
7.1 CVSS 3.1 High 2.8 4.2 security-advisories@github.com via NIST National Vulnerability Database
7.1 CVSS 3.1 High — — GitHub, Inc. via GitHub Security Advisories
7.1 CVSS 3.1 High — — GitHub_M via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-184

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
web/proxy/WAF logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first.

  • 2026
  • Fix documented
    Oct 14, 2026 · GitHub Security Advisories
  • Affected products added · pip/omnigent
    Oct 14, 2026 · GitHub Security Advisories
  • Affected products added · omnigent-ai/omnigent
    Oct 14, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 14, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 14, 2026
  • CVSS changed · 7.1
    Oct 14, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 14, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 14, 2026 · Alertas do Telegram
  • CVE published
    Aug 21, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 2× References added · Oct 14, 2026 – Oct 14, 2026
  • 1× Official description updated · Oct 14, 2026 – Oct 14, 2026

References

6 on the record

Elsewhere on this site

Omnigent-ai
every CVE for this vendor
CWE-184
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-62677 Omnigent: Unvalidated os_env.cwd in agent bundle yields arbitrary host filesystem access on runners without OMNIGENT_RUNNER_WORKSPACE Aug 21, 2026
  • CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE Aug 21, 2026
  • CVE-2026-62675 Omnigent: Uploaded Agent Bundle Allows Authenticated Runner RCE via Python Callable Tools Aug 21, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-62676 is "Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py", rated High. It affects Omnigent (Omnigent-ai); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 7.1 describes technical severity. EPSS 0.40% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.