39 matches found
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...
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...
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...
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...
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...
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 ...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...