Lucene search
K

1444 matches found

Positive Technologies
Positive Technologies
added 2026/06/01 12:0 a.m.15 views

PT-2026-45560

Nanobot prior to version 0.2.1 contains a server-side request forgery vulnerability in the web fetch tool that allows remote attackers to reach internal or private network hosts by supplying a URL that redirects to a loopback or private address via a 3xx Location header. Attackers can exploit the...

5.3CVSS5.8AI score0.00287EPSS
Exploits0References5
RedhatCVE
RedhatCVE
added 2026/05/30 8:13 a.m.13 views

CVE-2026-45373

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, although SSRF is validated against hostnames that resolve to private IPv6 addresses, when providing the IPV6 in‌‌ URL‌ as http://::1, the SSRF defenses do not work. This vulnerability is fixed in 0.8.26...

7.4CVSS5.8AI score0.00239EPSS
Exploits0References1
Snyk
Snyk
added 2026/05/29 10:29 p.m.6 views

Exposure of Sensitive System Information to an Unauthorized Control Sphere

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
Snyk
Snyk
added 2026/05/29 10:29 p.m.8 views

Exposure of Sensitive System Information to an Unauthorized Control Sphere

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Exposure of Sensitive System Information to an Unauthorized Control Sphere via the direct-prompt CLI. An attacker can access sensitive local...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:29 p.m.5 views

GHSA-5CXW-77WG-JRF3 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

Summary PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls MentionsParser.process.... The @url: handler then performs a direct urllib.request.urlopen request to the attacker-controlled URL...

5.5CVSS5.9AI score0.00014EPSS
Exploits0References2
Snyk
Snyk
added 2026/05/29 10:27 p.m.6 views

Server-side Request Forgery (SSRF)

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via improper URL validation the spidertools component. An attacker can access internal loopback-only HTTP...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
Snyk
Snyk
added 2026/05/29 10:27 p.m.3 views

Server-side Request Forgery (SSRF)

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
Github Security Blog
Github Security Blog
added 2026/05/29 10:27 p.m.25 views

PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings

Summary PraisonAI's spidertools URL validation can be bypassed using alternate loopback host encodings. The affected component is: text praisonaiagents/tools/spidertools.py The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled...

6.2AI score0.00014EPSS
Exploits0References2Affected Software2
OSV
OSV
added 2026/05/29 10:27 p.m.6 views

GHSA-5C6W-WWFQ-7QQM PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings

Summary PraisonAI's spidertools URL validation can be bypassed using alternate loopback host encodings. The affected component is: text praisonaiagents/tools/spidertools.py The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled...

5.5CVSS6.2AI score0.00014EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:16 p.m.4 views

GHSA-JMFC-HFJQ-PXCP stigmem-node's federation insecure transport settings may allow non-loopback cleartext federation

Impact Stigmem nodes with federation enabled could be configured to run without mTLS outside loopback-only local development. In affected deployments, federation traffic may traverse the network without the intended transport protection. Impacted users are operators who enabled federation and...

9.1CVSS5.8AI score
Exploits0References2
Github Security Blog
Github Security Blog
added 2026/05/29 10:16 p.m.18 views

stigmem-node's federation insecure transport settings may allow non-loopback cleartext federation

Impact Stigmem nodes with federation enabled could be configured to run without mTLS outside loopback-only local development. In affected deployments, federation traffic may traverse the network without the intended transport protection. Impacted users are operators who enabled federation and...

5.8AI score
Exploits0References2Affected Software1
OSV
OSV
added 2026/05/29 10:13 p.m.7 views

GHSA-FP6W-8WPG-74G5 stigmem-node: Auth-disabled deployments may grant broad anonymous access outside loopback

Impact Stigmem nodes configured with authentication disabled could grant the anonymous identity broad read/write/federation capabilities if exposed outside a loopback-only local development environment. Impacted users are operators who intentionally disabled authentication while binding the node ...

9.2CVSS5.8AI score
Exploits0References5
Github Security Blog
Github Security Blog
added 2026/05/29 10:13 p.m.18 views

stigmem-node: Auth-disabled deployments may grant broad anonymous access outside loopback

Impact Stigmem nodes configured with authentication disabled could grant the anonymous identity broad read/write/federation capabilities if exposed outside a loopback-only local development environment. Impacted users are operators who intentionally disabled authentication while binding the node ...

5.8AI score
Exploits0References5Affected Software1
NVD
NVD
added 2026/05/29 7:16 p.m.12 views

CVE-2026-46372

SillyTavern is a locally installed user interface that allows users to interact with text generation large language models, image generation engines, and text-to-speech voice models. Prior to 1.18.0, SillyTavern exposes /api/search/searxng, which accepts attacker-controlled baseUrl and uses it...

8.5CVSS0.00866EPSS
Exploits0References1
NVD
NVD
added 2026/05/29 7:16 p.m.10 views

CVE-2026-44652

SillyTavern is a locally installed user interface that allows users to interact with text generation large language models, image generation engines, and text-to-speech voice models. Prior to 1.18.0, corsProxyMiddleware forwards req.params.url directly into fetchurl, .... It only blocks circular...

6.9CVSS0.00375EPSS
Exploits0References1
NVD
NVD
added 2026/05/29 6:17 p.m.16 views

CVE-2026-45577

Neotoma provides versioned records that persist across agent runs. From 0.6.0 to before 0.11.1, Neotoma can treat public reverse-proxied requests as local when the app receives them over a loopback socket and no Bearer token is present. In affected deployments, the REST auth middleware can resolv...

6.9CVSS0.00249EPSS
Exploits0References2
ATTACKERKB
ATTACKERKB
added 2026/05/29 5:41 p.m.8 views

CVE-2026-46372

SillyTavern is a locally installed user interface that allows users to interact with text generation large language models, image generation engines, and text-to-speech voice models. Prior to 1.18.0, SillyTavern exposes /api/search/searxng, which accepts attacker-controlled baseUrl and uses it...

8.5CVSS5.8AI score0.00866EPSS
Exploits0References2Affected Software1
CVE
CVE
added 2026/05/29 4:53 p.m.16 views

CVE-2026-45577

Neotoma AG vulnerability CVE-2026-45577 affects versions 0.6.0 through before 0.11.1. When requests arrive via a loopback socket and are not Bearer-token authenticated, public reverse-proxied requests can be treated as local, causing the REST auth middleware to resolve unauthenticated requests as...

6.9CVSS5.8AI score0.00249EPSS
Exploits0References2
Vulnrichment
Vulnrichment
added 2026/05/29 4:53 p.m.14 views

CVE-2026-45577 Neotoma: Unauthenticated Inspector/API access via reverse-proxy loopback auth bypass

Neotoma provides versioned records that persist across agent runs. From 0.6.0 to before 0.11.1, Neotoma can treat public reverse-proxied requests as local when the app receives them over a loopback socket and no Bearer token is present. In affected deployments, the REST auth middleware can resolv...

6.9CVSS5.8AI score0.00249EPSS
Exploits0References2
Cvelist
Cvelist
added 2026/05/29 4:53 p.m.32 views

CVE-2026-45577 Neotoma: Unauthenticated Inspector/API access via reverse-proxy loopback auth bypass

Neotoma provides versioned records that persist across agent runs. From 0.6.0 to before 0.11.1, Neotoma can treat public reverse-proxied requests as local when the app receives them over a loopback socket and no Bearer token is present. In affected deployments, the REST auth middleware can resolv...

6.9CVSS0.00249EPSS
Exploits0References2
Rows per page
Query Builder