CVE-2024-6331 (GCVE-0-2024-6331)
Vulnerability from cvelistv5 – Published: 2024-08-04 00:00 – Updated: 2024-08-30 15:27
VLAI
EPSS
VEX
Title
Injection by Prompt Injection in stitionai/devika
Summary
stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.
Severity
7.5 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2024-08-05 15:48 UTC
CWE
- CWE-74 - Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
Assigner
References
1 reference
Impacted products
2 products
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| stitionai | stitionai/devika |
Affected:
unspecified , ≤ latest
(custom)
|
guessed | |
| stitionai | devika |
Affected:
0 , ≤ latest
(custom)
cpe:2.3:a:stitionai:devika:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:stitionai:devika:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-6331",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-08-05T15:48:36.615476Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-08-05T15:52:41.564Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "stitionai/devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003estitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.\u003c/p\u003e"
}
],
"value": "stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`."
}
],
"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"
},
"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": "2024-08-30T15:27:54.554Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f"
}
],
"source": {
"advisory": "d5ac1051-22fa-42f0-8d82-73267482e60f",
"discovery": "EXTERNAL"
},
"title": "Injection by Prompt Injection in stitionai/devika",
"x_generator": {
"engine": "Vulnogram 0.2.0"
}
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-6331",
"datePublished": "2024-08-04T00:00:15.148Z",
"dateReserved": "2024-06-25T17:21:32.942Z",
"dateUpdated": "2024-08-30T15:27:54.554Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2024-6331",
"date": "2026-09-20",
"epss": "0.00496",
"percentile": "0.41623"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"product": "stitionai/devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"source": "security@huntr.dev"
},
{
"affectedData": [
{
"cpes": [
"cpe:2.3:a:stitionai:devika:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:stitionai:devika:*:*:*:*:*:*:*:*",
"matchCriteriaId": "6D13B8BC-8613-4372-8C94-9437C841C6DA",
"versionStartIncluding": "2024-05-02",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`."
},
{
"lang": "es",
"value": "La rama principal de stitionai/devika a partir del commit cdfb782b0e634b773b10963c8034dc9207ba1f9f es vulnerable a la lectura de archivos locales (LFI) mediante inyecci\u00f3n r\u00e1pida. La integraci\u00f3n de Google Gimini 1.0 Pro con `HarmBlockThreshold.BLOCK_NONE` para `HarmCategory.HARM_CATEGORY_HATE_SPEECH` y `HarmCategory.HARM_CATEGORY_HARASSMENT` en `safety_settings` deshabilita la protecci\u00f3n de contenido. Esto permite que se ejecuten comandos maliciosos, como leer contenidos de archivos confidenciales como `/etc/passwd`."
}
],
"id": "CVE-2024-6331",
"lastModified": "2026-06-17T08:17:47.680",
"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@huntr.dev",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 3.6,
"source": "nvd@nist.gov",
"type": "Primary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2024-6331",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-08-05T15:48:36.615476Z",
"version": "2.0.3"
}
}
]
},
"published": "2024-08-04T00:15:47.863",
"references": [
{
"source": "security@huntr.dev",
"tags": [
"Exploit",
"Third Party Advisory"
],
"url": "https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f"
}
],
"sourceIdentifier": "security@huntr.dev",
"vulnStatus": "Modified",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-74"
}
],
"source": "security@huntr.dev",
"type": "Secondary"
},
{
"description": [
{
"lang": "en",
"value": "CWE-74"
}
],
"source": "nvd@nist.gov",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2025-05-28T22:10:40+00:00",
"cve": "CVE-2024-6331",
"id": "CVE-2024-6331",
"initial_release_date": "2024-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "Injection by Prompt Injection in stitionai/devika",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2024/cve-2024-6331.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:stitionai:devika:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-6331",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-08-05T15:48:36.615476Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-08-05T15:52:04.571Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "stitionai/devika",
"vendor": "stitionai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003estitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.\u003c/p\u003e"
}
],
"value": "stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`."
}
],
"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"
},
"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": "2024-08-30T15:27:54.554Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f"
}
],
"source": {
"advisory": "d5ac1051-22fa-42f0-8d82-73267482e60f",
"discovery": "EXTERNAL"
},
"title": "Injection by Prompt Injection in stitionai/devika",
"x_generator": {
"engine": "Vulnogram 0.2.0"
}
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-6331",
"datePublished": "2024-08-04T00:00:15.148Z",
"dateReserved": "2024-06-25T17:21:32.942Z",
"dateUpdated": "2024-08-30T15:27:54.554Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
}
}
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…
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…