{"id":"CVE-2024-5184","aliases":["EUVD-2024-46428","GHSA-27m7-5vm3-3prg"],"status":"published","title":"Prompt Injection in EmailGPT","description":"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":{"version":"4.0","score":8.5,"vector":"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","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00541,"percentile":0.45808,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-74"],"published":"2024-06-05T17:52:13Z","modified":"2026-06-17T08:15:21Z","products":[{"vendor":"emailgpt","product":"emailgpt"}],"references":[{"url":"https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-emailgpt.html","tags":["x_transferred","Third Party Advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2024-5184"},{"url":"https://github.com/advisories/GHSA-27m7-5vm3-3prg"}],"sources":{"cve":[{"id":"CVE-2024-5184","title":"Prompt Injection in EmailGPT","description":"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.","status":"published","published":"2024-06-05T17:52:13.608Z","modified":"2024-08-01T21:03:11.061Z","cvss":[{"version":"4.0","score":8.5,"vector":"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","level":"high","assessor":"cna"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-74"],"updated_at":"2026-11-02T14:34:01.286506Z"}],"euvd":[{"id":"EUVD-2024-46428","description":"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.","status":"published","published":"2024-06-05T17:52:13Z","modified":"2024-08-01T21:03:11Z","cvss":[{"version":"4.0","score":8.5,"vector":"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","level":"high"}],"updated_at":"2026-11-03T03:50:35.230694Z"}],"ghsa":[{"id":"GHSA-27m7-5vm3-3prg","title":"The EmailGPT service contains a prompt injection vulnerability. The service uses an API service...","description":"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.","status":"published","published":"2024-06-05T18:30:37Z","modified":"2024-06-05T18:30:43Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-74"],"updated_at":"2026-11-02T14:57:25.483683Z"}],"nvd":[{"id":"CVE-2024-5184","description":"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.","status":"published","published":"2024-06-05T18:15:11.993Z","modified":"2026-06-17T08:15:21.893Z","cvss":[{"version":"4.0","score":8.5,"vector":"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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"high","assessor":"secondary"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"secondary"},{"version":"3.1","score":9.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H","level":"critical","assessor":"primary"}],"cwes":["CWE-74"],"updated_at":"2026-11-02T14:10:03.465199Z"}]}}