> CVE-2026-62676 [HIGH]

« BACK_TO_HOME
PUBLISHED
2026-08-21 18:16
MODIFIED
2026-08-21 18:16
CVSS_SCORE V3
7.1
EPSS (Prob. Exploit)
0.40%
Top 67.1%
DATA SOURCES:
NVD 🔗 2026-08-21 CWE MITRE 🔗 2026-09-01 FIRST EPSS 🔗 2026-10-18 GITHUB 🔗 2026-10-29 OSV 🔗 2026-10-26

> 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.

> AFFECTED_PRODUCTS

ℹ️ Aucun produit affecté n'a encore été publié par NVD pour cette CVE.

> CVSS V3 METRICS

CVSS_VECTOR
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N
EXPLOITABILITY
2.8
IMPACT
4.2

> MÉTRIQUES CVSS DÉTAILLÉES

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N
Métrique Valeur Interprétation
AV (Vecteur d'Attaque)
Attack Vector
Network (N)
Exploit possible à distance via réseau (HTTP, API, etc.)
AC (Complexité d'Attaque)
Attack Complexity
Low (L)
Peu de conditions requises pour exploiter
PR (Privilèges Requis)
Privileges Required
Low (L)
Authentifié avec compte utilisateur basique
UI (Interaction Utilisateur)
User Interaction
None (N)
Aucune interaction utilisateur nécessaire
S (Périmètre)
Scope
Unchanged (U)
Impact reste dans le périmètre du composant compromis
C (Impact Confidentialité)
Confidentiality Impact
High (H)
Divulgation totale d'informations
I (Impact Intégrité)
Integrity Impact
Low (L)
Modification limitée des données possible
A (Impact Disponibilité)
Availability Impact
None (N)
Aucune interruption de service

> RÉSUMÉ DES IMPACTS

Confidentialité
High
Divulgation totale d'informations
Intégrité
Low
Modification limitée des données possible
Disponibilité
None
Aucune interruption de service

> WEAKNESSES

CWE-184

> CWE DETAILED DESCRIPTIONS

CWE-184: Incomplete List of Disallowed Inputs - The product implements a protection mechanism that relies on a list of inputs (or properties of inputs) that are not allowed by policy or otherwise require other action to neutralize before additional processing takes place, but the list is incomplete.

> GITHUB SECURITY ADVISORY

GHSA-7mqg-cx4g-x2rf HIGH

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

AFFECTED PACKAGES:
PIP / omnigent
< 0.3.0
Fixed in: 0.3.0

> OSV (GOOGLE OPEN SOURCE VULNERABILITIES)

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

AFFECTED PACKAGES:
Unknown / Unknown
1 versions affected
ALIASES:
GHSA-7mqg-cx4g-x2rf, PYSEC-2026-3873

> HISTORIQUE DES MODIFICATIONS

Première apparition
21/08/2026 18:16
Source: NVD
📊 ENRICHISSEMENT 01/09/2026 06:02
CWE
Champ modifié: Description CWE
Ancienne valeur:
N/A
Nouvelle valeur:
CWE-184: Incomplete List of Disallowed Inputs - The product implements a protection mechanism that relies on a list of inputs (or properties of inputs) that are not allowed by policy or otherwise requ...
Total des modifications: 1 Dernière mise à jour: 1 month ago

> REFERENCES

https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe1...
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
« BACK_TO_HOME