| NVIDIA garak | Fixed a crash in z-rating evaluation caused by a removed calibration method. PR #1794 ↗ | Merged |
| NVIDIA garak | Added a regression test to keep duplicate configuration files out of scan reports. PR #1791 ↗ | Merged |
| Promptfoo | Fixed evaluation configs silently dropping distinct function-based providers. PR #9402 ↗ | Merged |
| Presidio | Fixed a YAML default that scored deny-list matches at zero, silently missing PII at positive thresholds. PR #2254 ↗ | Merged |
| Anthropic Claude Code | Credential Guard: a proposed guardrail to detect hardcoded secrets in coding-agent tool calls. PR #62099 ↗ | Open PR |
| Anthropic Claude Cookbooks | Proposed secure Claude Code routines for avoiding credential leakage. PR #667 ↗ | Open PR |
| Future AGI | Proposed an indirect prompt-injection guardrail for the AI gateway. PR #851 ↗ | Open PR |
| NVIDIA NeMo Guardrails | Proposed synchronization for embedding batches. PR #1921 ↗ | Open PR |
| ProtectAI ModelScan | Proposed a fix for settings-file generation producing an empty file. PR #349 ↗ | Open PR |
| ETH AgentDojo | Proposed removing an unused processed-message list from the prompt-injection detector. PR #195 ↗ | Open PR |
| NVIDIA garak | Proposed structured CLI exit codes for automation and failure handling. PR #1790 ↗ | Open PR |
| NVIDIA garak | Proposed lint configuration and core-module fixes. PR #1793 ↗ | Open PR |