FKIE_CVE-2026-62677
Vulnerability from fkie_nvd - Published: 2026-08-21 18:16 - Updated: 2026-10-14 19:10
Severity
Summary
Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, an authenticated user can upload a session-scoped agent bundle with an absolute or traversal-containing os_env.cwd value because omnigent/spec/parser.py stores the value verbatim and omnigent/spec/validator.py does not constrain it. On a runner where OMNIGENT_RUNNER_WORKSPACE is unset, omnigent/runner/resource_registry.py preserves the attacker-controlled path and omnigent/inner/os_env.py uses the resolved path as the environment root and copytree source. The _assert_within_cwd check then treats that attacker-selected root as trusted, allowing sys_os_read, write, edit, and shell tools to access runner files and environment secrets outside the intended workspace. This issue is fixed in version 0.3.0.
References
Impacted products
| Vendor | Product | Version |
|---|
{
"affected": [
{
"affectedData": [
{
"product": "omnigent",
"vendor": "omnigent-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.3.0"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, an authenticated user can upload a session-scoped agent bundle with an absolute or traversal-containing os_env.cwd value because omnigent/spec/parser.py stores the value verbatim and omnigent/spec/validator.py does not constrain it. On a runner where OMNIGENT_RUNNER_WORKSPACE is unset, omnigent/runner/resource_registry.py preserves the attacker-controlled path and omnigent/inner/os_env.py uses the resolved path as the environment root and copytree source. The _assert_within_cwd check then treats that attacker-selected root as trusted, allowing sys_os_read, write, edit, and shell tools to access runner files and environment secrets outside the intended workspace. This issue is fixed in version 0.3.0."
},
{
"lang": "es",
"value": "Omnigent es un framework de agente de IA de c\u00f3digo abierto y un meta-arn\u00e9s para orquestar agentes de codificaci\u00f3n. Antes de la versi\u00f3n 0.3.0, un usuario autenticado puede cargar un paquete de agente con \u00e1mbito de sesi\u00f3n con un valor os_env.cwd absoluto o que contiene una ruta de acceso transversal porque omnigent/spec/parser.py almacena el valor textualmente y omnigent/spec/validator.py no lo restringe. En un ejecutor donde OMNIGENT_RUNNER_WORKSPACE no est\u00e1 configurado, omnigent/runner/resource_registry.py preserva la ruta controlada por el atacante y omnigent/inner/os_env.py utiliza la ruta resuelta como la ra\u00edz del entorno y la fuente de copytree. La verificaci\u00f3n _assert_within_cwd luego trata esa ra\u00edz seleccionada por el atacante como confiable, permitiendo que las herramientas sys_os_read, write, edit y shell accedan a los archivos del ejecutor y a los secretos del entorno fuera del espacio de trabajo previsto. Este problema se corrige en la versi\u00f3n 0.3.0."
}
],
"id": "CVE-2026-62677",
"lastModified": "2026-10-14T19:10:00.297",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-62677",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-21T21:00:11.438418Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-08-21T18:16:49.887",
"references": [
{
"source": "security-advisories@github.com",
"url": "https://github.com/omnigent-ai/omnigent/commit/7ca0cca3c9a65c04c489edf68f0e080424a26868"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/omnigent-ai/omnigent/pull/1417"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-p8rw-8qj3-hf33"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-22"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
Loading…
Loading…
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.