CVE-2025-51482 (GCVE-0-2025-51482)
Vulnerability from cvelistv5 – Published: 2025-07-22 00:00 – Updated: 2025-07-22 17:54Summary
Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2025-07-22 17:51 UTC
CWE
- n/a
- CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
References
Shadowserver
Known Exploited Vulnerability - GCVE BCP-07 Compliant
KEV entry ID: 1f25a4a5-0440-4b26-ad98-57807f7f76da
Exploited: Yes
Characteristics
Severity:
88.0
Timestamps
First Seen: 2025-10-24
Asserted: 2025-10-24
Last Seen: 2025-11-03
Scope
Asset Exposure: ['internet-facing']
Notes: Affected: Letta / Letta | Class: ai-system | Severity: High (CVSS 8.8) | IoT: no | In CISA KEV: no | Honeypot connections on 2025-11-03: 6
Evidence
Type: Honeypot
Signal: In The Wild Attempts
Confidence: 70%
Source: shadowserver
Details
| 1D | 1 |
|---|---|
| Iot | no |
| Feed | Shadowserver Foundation honeypot/exploited-vulnerabilities |
| Type | http-scan |
| Class | ai-system |
| 7D Avg | 0 |
| Vendor | Letta |
| 30D Avg | 0 |
| 90D Avg | 0 |
| Product | Letta |
| Cisa Kev | no |
| Connections | 6 |
| Observation Date | 2025-11-03 |
| Vulnerability Class | CVSS |
| Vulnerability Score | 8.8 |
| Vulnerability Severity | High |
References
Created: 2026-07-01 07:18 UTC
| Updated: 2026-07-01 12:45 UTC
{
"containers": {
"adp": [
{
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2025-51482",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-07-22T17:51:51.972192Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-07-22T17:54:13.905Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-07-22T16:53:09.940Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/letta-ai/letta"
},
{
"url": "https://github.com/letta-ai/letta/pull/2630"
},
{
"url": "https://www.gecko.security/blog/cve-2025-51482"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2025-51482",
"datePublished": "2025-07-22T00:00:00.000Z",
"dateReserved": "2025-06-16T00:00:00.000Z",
"dateUpdated": "2025-07-22T17:54:13.905Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2025-51482",
"date": "2026-09-20",
"epss": "0.01862",
"percentile": "0.78317"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"source": "cve@mitre.org"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:letta:letta:0.7.12:*:*:*:*:*:*:*",
"matchCriteriaId": "C9B6F281-2D53-4FF0-8693-67AC55F4C5C6",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions."
},
{
"lang": "es",
"value": "Ejecuci\u00f3n remota de c\u00f3digo en letta.server.rest_api.routers.v1.tools.run_tool_from_source en letta-ai Letta 0.7.12 permite a atacantes remotos ejecutar c\u00f3digo Python arbitrario y comandos del sistema a trav\u00e9s de payloads manipuladas en el endpoint /v1/tools/run, eludiendo las restricciones de entorno de pruebas previstas."
}
],
"id": "CVE-2025-51482",
"lastModified": "2026-06-17T09:35:37.930",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2025-51482",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-07-22T17:51:51.972192Z",
"version": "2.0.3"
}
}
]
},
"published": "2025-07-22T17:15:33.750",
"references": [
{
"source": "cve@mitre.org",
"tags": [
"Product"
],
"url": "https://github.com/letta-ai/letta"
},
{
"source": "cve@mitre.org",
"tags": [
"Exploit",
"Issue Tracking",
"Patch",
"Vendor Advisory"
],
"url": "https://github.com/letta-ai/letta/pull/2630"
},
{
"source": "cve@mitre.org",
"tags": [
"Exploit",
"Third Party Advisory"
],
"url": "https://www.gecko.security/blog/cve-2025-51482"
}
],
"sourceIdentifier": "cve@mitre.org",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-94"
}
],
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2025-07-24T00:23:41+00:00",
"cve": "CVE-2025-51482",
"id": "CVE-2025-51482",
"initial_release_date": "2025-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "CVE-2025-51482",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-51482.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2025-51482",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-07-22T17:51:51.972192Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-07-22T17:52:47.184Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-07-22T16:53:09.940Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/letta-ai/letta"
},
{
"url": "https://github.com/letta-ai/letta/pull/2630"
},
{
"url": "https://www.gecko.security/blog/cve-2025-51482"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2025-51482",
"datePublished": "2025-07-22T00:00:00.000Z",
"dateReserved": "2025-06-16T00:00:00.000Z",
"dateUpdated": "2025-07-22T17:54:13.905Z",
"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…