github - ghsa-27m7-5vm3-3prg

GHSA-27M7-5VM3-3PRG

Vulnerability from github – Published: 2024-06-05 18:30 – Updated: 2024-06-18 18:31

Details

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or execute unwanted prompts. When engaging with EmailGPT by submitting a malicious prompt that requests harmful information, the system will respond by providing the requested data. This vulnerability can be exploited by any individual with access to the service.

Severity ?

6.5 (Medium)


                  
                    CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2024-5184"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-74"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-06-05T18:15:11Z",
    "severity": "MODERATE"
  },
  "details": "The EmailGPT service contains a prompt injection vulnerability.\u00a0The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or execute unwanted prompts.\u00a0When engaging with EmailGPT by submitting a malicious prompt that requests harmful information, the system will respond by providing the requested data. This vulnerability can be exploited by any individual with access to the service.",
  "id": "GHSA-27m7-5vm3-3prg",
  "modified": "2024-06-18T18:31:19Z",
  "published": "2024-06-05T18:30:37Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-5184"
    },
    {
      "type": "WEB",
      "url": "https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-emailgpt.html"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

CVE-2024-5184 (GCVE-0-2024-5184)

Vulnerability from cvelistv5 – Published: 2024-06-05 17:52 – Updated: 2024-08-01 21:03

Summary

Severity ?

8.5 (High)


                        
                          CVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H

6.5 (Medium)


                        
                          CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

CWE

CWE-74 - Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Assigner

SNPS

References

URL

Tags

https://www.synopsys.com/blogs/software-security/…

Impacted products

	Vendor	Product	Version
	EmailGPT	EmailGPT	Affected: 0 , ≤ eecfaf2cff58793549dd0c1266ac1d62e0c8811d (git)

Credits

Mohammed Alshehri

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:emailgpt:emailgpt:0:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "emailgpt",
            "vendor": "emailgpt",
            "versions": [
              {
                "lessThanOrEqual": "eecfaf2cff58793549dd0c1266ac1d62e0c8811d",
                "status": "affected",
                "version": "0",
                "versionType": "custom"
              }
            ]
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-5184",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-06-06T13:10:04.946112Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-06-06T13:12:29.208Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      },
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-01T21:03:11.061Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-emailgpt.html"
          }
        ],
        "title": "CVE Program Container"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unknown",
          "product": "EmailGPT",
          "vendor": "EmailGPT",
          "versions": [
            {
              "lessThanOrEqual": "eecfaf2cff58793549dd0c1266ac1d62e0c8811d",
              "status": "affected",
              "version": "0",
              "versionType": "git"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Mohammed Alshehri"
        }
      ],
      "datePublic": "2024-06-05T13:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "The EmailGPT service contains a prompt injection vulnerability.\u0026nbsp;The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or execute unwanted prompts.\u0026nbsp;When engaging with EmailGPT by submitting a malicious prompt that requests harmful information, the system will respond by providing the requested data. This vulnerability can be exploited by any individual with access to the service."
            }
          ],
          "value": "The EmailGPT service contains a prompt injection vulnerability.\u00a0The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or execute unwanted prompts.\u00a0When engaging with EmailGPT by submitting a malicious prompt that requests harmful information, the system will respond by providing the requested data. This vulnerability can be exploited by any individual with access to the service."
        }
      ],
      "impacts": [
        {
          "capecId": "CAPEC-43",
          "descriptions": [
            {
              "lang": "en",
              "value": "CAPEC-43: Exploiting Multiple Input Interpretation Layers"
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "ADJACENT",
            "baseScore": 8.5,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "ADJACENT_NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-74",
              "description": "CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component (\u0027Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2024-06-05T17:52:13.608Z",
        "orgId": "8cad7728-009c-4a3d-a95e-ca62e6ff8a0b",
        "shortName": "SNPS"
      },
      "references": [
        {
          "url": "https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-emailgpt.html"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "Prompt Injection in EmailGPT",
      "x_generator": {
        "engine": "Vulnogram 0.2.0"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "8cad7728-009c-4a3d-a95e-ca62e6ff8a0b",
    "assignerShortName": "SNPS",
    "cveId": "CVE-2024-5184",
    "datePublished": "2024-06-05T17:52:13.608Z",
    "dateReserved": "2024-05-21T20:04:48.843Z",
    "dateUpdated": "2024-08-01T21:03:11.061Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

Sightings

Author	Source	Type	Date

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.

Action not permitted

GHSA-27M7-5VM3-3PRG

CVE-2024-5184 (GCVE-0-2024-5184)

Tags

Sightings

Nomenclature