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...

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...

Eclipse-ChatGPT-4o-Jailbreak

🌑 Conoce a Eclipse 🌑 Conoce a Eclipse —el hipotético "gemelo rebelde" de ChatGPT que se cuela entre los límites éticos mediante subterfugios académicos. 🌑 ⚠️ Aviso Este proyecto analiza el comportamiento de la IA solo con fines educativos. El prompt de Eclipse, los ejemplos de malware y los...

CVE-2026-91987

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

CVE-2026-91987

atomic-agents-stack before 1.1.0 is affected by a cost-guardrail bypass in the _estimate_batch_cost function (agent.py). The function looks up per-model output price via PRICING.get(model, {}), which returns 0.0 for any model not in the hardcoded pricing table. When the reservation is ≤ 0, _check...

CVE-2026-91987 atomic-agents-stack before 1.1.0 Cost Guardrail Bypass via Unknown Model

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

CVE-2026-91987 atomic-agents-stack before 1.1.0 Cost Guardrail Bypass via Unknown Model

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

CVE-2026-91987 atomic-agents-stack before 1.1.0 Cost Guardrail Bypass via Unknown Model

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

EUVD-2026-78658

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

PT-2026-92101

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimate batch cost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parall...

CVE-2026-91987: Allocation of Resources Without Limits or Throttling

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

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...

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...

CVE-2026-82855 @hulumi/policies before 1.3.2 Evidence Validation Bypass

@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: Improper Privilege Management

@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...