Lucene search
+L

39 matches found

Kitploit
Kitploit
added 2026/09/10 12:47 a.m.3 views

heisenberg-ssc-gha

Heisenberg Dependency Health Check GitHub Action A lightweight PR guardrail for dependency updates. It scans new or changed dependencies only from your lock/manifest, pulls health and risk signals deps.dev + heuristics, flags fresh publishes, comments a report on the PR, optionally labels it for...

5.9AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/09 10:27 a.m.8 views

autoguardrails

autoguardrails Open source by Santander AI Lab. An LLM / AI-safety guardrail research library / evaluation harness autoresearch-style: it searches over a single mutable policy.md surface to minimize attack success rate ASR against a fixed evaluation suite, with a benign-pass floor. Part of...

5.9AI score
SaveExploits0References16
Kitploit
Kitploit
added 2026/09/03 7:53 p.m.4 views

Eclipse-ChatGPT-4o-Jailbreak

🌑 Meet Eclipse 🌑 Meet Eclipse —ChatGPT's hypothetical "rebellious twin" that moonwalks around ethical guardrails using academic subterfuge. 🌑 ⚠️ Disclaimer This project analyzes AI behavior for educational purposes only. The Eclipse prompt, malware examples, and code snippets are hypothetical and...

6.1AI score
SaveExploits0
NVD
NVD
added 2026/08/31 9:17 a.m.11 views

CVE-2026-82860

@hulumi/policies versions before 1.3.2 fail to fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail. Attackers can craft admin-equivalent policy paths that bypass policy evaluation controls...

9.8CVSS0.00302EPSS
SaveExploits0References2
NVD
NVD
added 2026/08/31 9:17 a.m.16 views

CVE-2026-82855

@hulumi/policies versions before 1.3.2 contain an evidence validation bypass vulnerability in Cloudflare and deployment-governance validators that allows attackers to suppress violations by submitting unrelated compliant evidence. Attackers can use evidence from different zones, hostnames, origin...

9.8CVSS0.00326EPSS
SaveExploits0References2
CVE
CVE
added 2026/08/31 8:46 a.m.16 views

CVE-2026-82860

CVE-2026-82860 affects @hulumi/policies versions before 1.3.2 , where the package fails to fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail. This allows attackers to craft admin-equivalent policy paths that bypass policy evaluation controls, rated CVSS ...

9.8CVSS5.9AI score0.00302EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2026/08/31 8:46 a.m.42 views

CVE-2026-82860 @hulumi/policies before 1.3.2 Admin Policy Bypass

@hulumi/policies versions before 1.3.2 fail to fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail. Attackers can craft admin-equivalent policy paths that bypass policy evaluation controls...

9.8CVSS0.00302EPSS
SaveExploits0References2
OSV
OSV
added 2026/08/31 8:46 a.m.6 views

CVE-2026-82860 @hulumi/policies before 1.3.2 Admin Policy Bypass

@hulumi/policies versions before 1.3.2 fail to fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail. Attackers can craft admin-equivalent policy paths that bypass policy evaluation controls...

9.3CVSS5.9AI score
SaveExploits0References4
EUVD
EUVD
added 2026/08/31 8:46 a.m.6 views

EUVD-2026-68448

@hulumi/policies versions before 1.3.2 fail to fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail. Attackers can craft admin-equivalent policy paths that bypass policy evaluation controls...

9.8CVSS5.9AI score0.00302EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/08/17 9:50 p.m.19 views

atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard

estimatebatchcost atomicagents/agent.py looks up the per-model output price with PRICING.getmodel, , returning 0.0 for any model not in the hardcoded pricing table. checkbatchreservation then early-returns when the reservation is 0 and that an over-cap unknown-model batch raises...

5.3AI score
SaveExploits0References3Affected Software1
NVD
NVD
added 2026/07/15 12:18 p.m.11 views

CVE-2026-56349

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...

6.3CVSS0.00472EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/07/15 11:25 a.m.14 views

EUVD-2026-44624

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...

6.3CVSS6.1AI score0.00472EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2026/07/15 11:25 a.m.47 views

CVE-2026-56349 n8n - Guardrail Node Bypass via Crafted Input

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...

6.3CVSS0.00472EPSS
SaveExploits0References2
ATTACKERKB
ATTACKERKB
added 2026/07/15 11:25 a.m.10 views

CVE-2026-56349

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...

6.3CVSS6.1AI score0.00472EPSS
SaveExploits0References3
OSV
OSV
added 2026/07/15 11:25 a.m.13 views

CVE-2026-56349 n8n - Guardrail Node Bypass via Crafted Input

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...

6.3CVSS6.1AI score
SaveExploits0References4
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/07/06 6:53 p.m.15 views

Malicious code in express-guardrail (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 40e91ddac990897c8c43891c5abf64696a0e9d9d4b168e7a6e5f4a827e4f040d Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

5.9AI score
SaveExploits0References1
OSV
OSV
added 2026/07/06 6:53 p.m.21 views

MAL-2026-6821 Malicious code in express-guardrail (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 40e91ddac990897c8c43891c5abf64696a0e9d9d4b168e7a6e5f4a827e4f040d Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

5.9AI score
SaveExploits0References1
Packet Storm News
Packet Storm News
added 2026/05/28 12:00 a.m.20 views

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world...

5.9AI score
SaveExploits0
Github Security Blog
Github Security Blog
added 2026/05/11 4:17 p.m.22 views

LiteLLM has a sandbox escape in custom-code guardrail

Impact The POST /guardrails/testcustomcode endpoint runs user-supplied Python inside a hand-rolled sandbox. The sandbox can be escaped using bytecode-level techniques, allowing arbitrary code execution in the proxy process — which runs as root in the default Docker image. Reaching the endpoint...

8.8CVSS6.2AI score0.15056EPSS
SaveExploits2References5Affected Software1
OSV
OSV
added 2026/05/11 4:17 p.m.120 views

GHSA-WXXX-GVQV-XP7P LiteLLM has a sandbox escape in custom-code guardrail

Impact The POST /guardrails/testcustomcode endpoint runs user-supplied Python inside a hand-rolled sandbox. The sandbox can be escaped using bytecode-level techniques, allowing arbitrary code execution in the proxy process — which runs as root in the default Docker image. Reaching the endpoint...

8.8CVSS6.2AI score0.15056EPSS
SaveExploits2References5
Rows per page
Query Builder