GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

CVE-2026-53710 (GCVE-0-2026-53710)

Vulnerability from cvelistv5 – Published: 2026-09-15 16:47 – Updated: 2026-09-15 19:45
VLAI
Title
MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server
Summary
MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2.
Severity
10 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-15 19:16 UTC
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
  • CWE-693 - Protection Mechanism Failure
Assigner
References
Impacted products
Vendor Product Version CPE status
IBM mcp-context-forge Affected: < 1.0.2
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-53710",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-15T19:16:37.898454Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-15T19:45:23.818Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "mcp-context-forge",
          "vendor": "IBM",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.0.2"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 10,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-693",
              "description": "CWE-693: Protection Mechanism Failure",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-15T16:47:41.085Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
        },
        {
          "name": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
        },
        {
          "name": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2"
        }
      ],
      "source": {
        "advisory": "GHSA-xm98-3vcf-fph7",
        "discovery": "UNKNOWN"
      },
      "title": "MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-53710",
    "datePublished": "2026-09-15T16:47:41.085Z",
    "dateReserved": "2026-06-10T16:43:31.241Z",
    "dateUpdated": "2026-09-15T19:45:23.818Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-53710",
      "date": "2026-09-16",
      "epss": "0.00827",
      "percentile": "0.55675"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-53710\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-09-15T17:17:19.117\",\"lastModified\":\"2026-09-15T20:17:17.743\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"IBM\",\"product\":\"mcp-context-forge\",\"versions\":[{\"version\":\"\u003c 1.0.2\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H\",\"baseScore\":10.0,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":6.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-09-15T19:16:37.898454Z\",\"id\":\"CVE-2026-53710\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"},{\"lang\":\"en\",\"value\":\"CWE-693\"}]}],\"references\":[{\"url\":\"https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7\",\"source\":\"security-advisories@github.com\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-53710\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-15T19:16:37.898454Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-15T19:16:39.303Z\"}}], \"cna\": {\"title\": \"MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server\", \"source\": {\"advisory\": \"GHSA-xm98-3vcf-fph7\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 10, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"IBM\", \"product\": \"mcp-context-forge\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.0.2\"}]}], \"references\": [{\"url\": \"https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7\", \"name\": \"https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89\", \"name\": \"https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2\", \"name\": \"https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-693\", \"description\": \"CWE-693: Protection Mechanism Failure\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-09-15T16:47:41.085Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-53710\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-09-15T19:45:23.818Z\", \"dateReserved\": \"2026-06-10T16:43:31.241Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-09-15T16:47:41.085Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.


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.