CVE-2026-47395 (GCVE-0-2026-47395)
Vulnerability from cvelistv5
Published
2026-07-21 15:52
Modified
2026-07-21 17:15
Severity ?
VLAI Severity ?
EPSS score ?
CWE
- CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.
References
| URL | Tags | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||
Impacted products
| Vendor | Product | Version | |||||||
|---|---|---|---|---|---|---|---|---|---|
| MervinPraison | PraisonAI |
Version: < 4.6.40 |
|||||||
|
|||||||||
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47395",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T17:09:32.354388Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:15:13.196Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI\u0027s direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:\u003chttp-or-https-url\u003e`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator\u0027s machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 5.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:52:52.682Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-5cxw-77wg-jrf3",
"discovery": "UNKNOWN"
},
"title": "PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47395",
"datePublished": "2026-07-21T15:52:52.682Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T17:15:13.196Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-47395\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-07-21T17:09:32.354388Z\"}}}], \"references\": [{\"url\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-07-21T17:09:44.385Z\"}}], \"cna\": {\"title\": \"PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context\", \"source\": {\"advisory\": \"GHSA-5cxw-77wg-jrf3\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 5.5, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"MervinPraison\", \"product\": \"PraisonAI\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 4.6.40\"}]}, {\"vendor\": \"MervinPraison\", \"product\": \"praisonaiagents\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.6.40\"}]}], \"references\": [{\"url\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3\", \"name\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/MervinPraison/PraisonAI/pull/1684\", \"name\": \"https://github.com/MervinPraison/PraisonAI/pull/1684\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6\", \"name\": \"https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI\u0027s direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:\u003chttp-or-https-url\u003e`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator\u0027s machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-200\", \"description\": \"CWE-200: Exposure of Sensitive Information to an Unauthorized Actor\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-07-21T15:52:52.682Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-47395\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-07-21T17:15:13.196Z\", \"dateReserved\": \"2026-05-19T19:22:45.729Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-07-21T15:52:52.682Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.
Loading…
Loading…