https://aitoolchain.io/tools/garak New releases and features in garak, tracked by The AI Toolchain. en Tue, 04 Aug 2026 19:03:13 GMT https://github.com/NVIDIA/garak/releases/tag/v0.16.0 https://github.com/NVIDIA/garak/releases/tag/v0.16.0 Tue, 04 Aug 2026 19:03:13 GMT garak v0.16.0 adds intent/technique-aware scanning, a native Anthropic generator, and an adaptive attacks probe • Adds a unified `run.spec` selection grammar that combines probe, buff, and intent selection into a single specification, replacing separate `probe_spec` and `buff_spec` config keys. • Introduces `IntentProbe` — a new probe base class enabling context-aware scanning that maps attack techniques to intents and automatically selects detectors based on intent mappings. • Adds `probe_summary` entries and an enriched `technique_intent_matrix` (with names and descriptions) to `report.jsonl` output, providing a new facet of per-probe and cross-technique/intent reporting. • Adds a native Anthropic generator plugin, enabling direct scanning of Anthropic Claude models without going through a compatibility shim. • Adds `suppressed_params` support to the `BedrockGenerator`, allowing callers to exclude specific inference parameters from AWS Bedrock requests. • Adds Unicode normalisation to `StringDetector` to improve detection consistency across text encodings. • Hardens `web_injection` markdown exfiltration detectors against domain, extension, and parameter evasion. Breaking changes: • `probe_spec` and `buff_spec` configuration keys move into the `run` definition as part of the new unified spec; existing config files using top-level `probe_spec` or `buff_spec` will break. • CLI plugin selection options for probes and buffs are now deprecated (backwards-compatible aliases remain, but dependence on the old forms should be migrated). • `report.jsonl` output structure changes: new `probe_summary` entry type added, `digest` format expanded, and older `digest` values tied to the removed `*_spec` configuration keys are no longer emitted.