CVE-2026-77604 (GCVE-0-2026-77604)
Vulnerability from cvelistv5 – Published: 2026-11-05 20:10 – Updated: 2026-11-09 22:51
VLAI
EPSS
VEX
Title
Code Graph RAG: MCP paginated read_file path traversal / arbitrary file read
Summary
Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.read_file implementation in codebase_rag/mcp/tools.py joins attacker-controlled file_path input to project_root without resolving and verifying containment when offset or limit selects the paginated branch. An absolute path causes pathlib to discard the configured root, while relative traversal can also resolve outside it. The protected non-paginated branch uses validate_project_path, but the paginated branch bypasses that validation before opening the path. An unauthenticated caller of a network-exposed HTTP MCP server can therefore read arbitrary UTF-8-readable files available to the server process, including credentials, environment data, private keys, source, and configuration; local callers through the stdio transport can reach the same vulnerable code path. This issue is fixed in version 0.0.345.
Severity
7.5 (High)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-09 22:50 UTC
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/vitali87/code-graph-rag/securi… | x_refsource_CONFIRM |
| https://github.com/vitali87/code-graph-rag/commit… | x_refsource_MISC |
| https://github.com/vitali87/code-graph-rag/releas… | x_refsource_MISC |
| https://github.com/openemr/openemr/security/advis… | exploit |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| vitali87 | code-graph-rag |
Affected:
< 0.0.345
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-77604",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T22:50:42.309586Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-09T22:51:03.789Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/openemr/openemr/security/advisories/GHSA-5h9g-m7q2-pv45"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "code-graph-rag",
"vendor": "vitali87",
"versions": [
{
"status": "affected",
"version": "\u003c 0.0.345"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.read_file implementation in codebase_rag/mcp/tools.py joins attacker-controlled file_path input to project_root without resolving and verifying containment when offset or limit selects the paginated branch. An absolute path causes pathlib to discard the configured root, while relative traversal can also resolve outside it. The protected non-paginated branch uses validate_project_path, but the paginated branch bypasses that validation before opening the path. An unauthenticated caller of a network-exposed HTTP MCP server can therefore read arbitrary UTF-8-readable files available to the server process, including credentials, environment data, private keys, source, and configuration; local callers through the stdio transport can reach the same vulnerable code path. This issue is fixed in version 0.0.345."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-05T20:10:19.957Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vitali87/code-graph-rag/security/advisories/GHSA-vvr2-h2jp-838m",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vitali87/code-graph-rag/security/advisories/GHSA-vvr2-h2jp-838m"
},
{
"name": "https://github.com/vitali87/code-graph-rag/commit/6541e920a27961fa8f3ff49ef38c0e0bd09cd626",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vitali87/code-graph-rag/commit/6541e920a27961fa8f3ff49ef38c0e0bd09cd626"
},
{
"name": "https://github.com/vitali87/code-graph-rag/releases/tag/v0.0.345",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vitali87/code-graph-rag/releases/tag/v0.0.345"
}
],
"source": {
"advisory": "GHSA-vvr2-h2jp-838m",
"discovery": "UNKNOWN"
},
"title": "Code Graph RAG: MCP paginated read_file path traversal / arbitrary file read"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-77604",
"datePublished": "2026-11-05T20:10:19.957Z",
"dateReserved": "2026-08-20T20:48:20.507Z",
"dateUpdated": "2026-11-09T22:51:03.789Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-77604",
"date": "2026-11-17",
"epss": "0.00391",
"percentile": "0.33807"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "code-graph-rag",
"vendor": "vitali87",
"versions": [
{
"status": "affected",
"version": "\u003c 0.0.345"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.read_file implementation in codebase_rag/mcp/tools.py joins attacker-controlled file_path input to project_root without resolving and verifying containment when offset or limit selects the paginated branch. An absolute path causes pathlib to discard the configured root, while relative traversal can also resolve outside it. The protected non-paginated branch uses validate_project_path, but the paginated branch bypasses that validation before opening the path. An unauthenticated caller of a network-exposed HTTP MCP server can therefore read arbitrary UTF-8-readable files available to the server process, including credentials, environment data, private keys, source, and configuration; local callers through the stdio transport can reach the same vulnerable code path. This issue is fixed in version 0.0.345."
}
],
"id": "CVE-2026-77604",
"lastModified": "2026-11-12T22:18:51.470",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 3.6,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-77604",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T22:50:42.309586Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-11-05T20:18:00.017",
"references": [
{
"source": "security-advisories@github.com",
"url": "https://github.com/vitali87/code-graph-rag/commit/6541e920a27961fa8f3ff49ef38c0e0bd09cd626"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/vitali87/code-graph-rag/releases/tag/v0.0.345"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/vitali87/code-graph-rag/security/advisories/GHSA-vvr2-h2jp-838m"
},
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"url": "https://github.com/openemr/openemr/security/advisories/GHSA-5h9g-m7q2-pv45"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-22"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-77604",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T22:50:42.309586Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-09T22:50:58.146Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/openemr/openemr/security/advisories/GHSA-5h9g-m7q2-pv45"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "code-graph-rag",
"vendor": "vitali87",
"versions": [
{
"status": "affected",
"version": "\u003c 0.0.345"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.read_file implementation in codebase_rag/mcp/tools.py joins attacker-controlled file_path input to project_root without resolving and verifying containment when offset or limit selects the paginated branch. An absolute path causes pathlib to discard the configured root, while relative traversal can also resolve outside it. The protected non-paginated branch uses validate_project_path, but the paginated branch bypasses that validation before opening the path. An unauthenticated caller of a network-exposed HTTP MCP server can therefore read arbitrary UTF-8-readable files available to the server process, including credentials, environment data, private keys, source, and configuration; local callers through the stdio transport can reach the same vulnerable code path. This issue is fixed in version 0.0.345."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-05T20:10:19.957Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vitali87/code-graph-rag/security/advisories/GHSA-vvr2-h2jp-838m",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vitali87/code-graph-rag/security/advisories/GHSA-vvr2-h2jp-838m"
},
{
"name": "https://github.com/vitali87/code-graph-rag/commit/6541e920a27961fa8f3ff49ef38c0e0bd09cd626",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vitali87/code-graph-rag/commit/6541e920a27961fa8f3ff49ef38c0e0bd09cd626"
},
{
"name": "https://github.com/vitali87/code-graph-rag/releases/tag/v0.0.345",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vitali87/code-graph-rag/releases/tag/v0.0.345"
}
],
"source": {
"advisory": "GHSA-vvr2-h2jp-838m",
"discovery": "UNKNOWN"
},
"title": "Code Graph RAG: MCP paginated read_file path traversal / arbitrary file read"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-77604",
"datePublished": "2026-11-05T20:10:19.957Z",
"dateReserved": "2026-08-20T20:48:20.507Z",
"dateUpdated": "2026-11-09T22:51:03.789Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
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.
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.
Loading…