July 16, 2026

Agent Output available in beta for all orgs

14 new 11 improved 24 fixed

Slash-command palette in the web chat composer. Typing / opens a fuzzy-filtered overlay with built-in actions (/new, /clear, /rewind, /model, /agent, and more) plus dynamically-discovered skills. (dreadnode/dreadnode-tiger#1923)
@-mention agent picker in the chat composer. Type @ to open an inline agent picker navigable by keyboard or mouse; selecting an agent inserts it as a mention in your message. (dreadnode/dreadnode-tiger#1927)
/background launcher in the web chat composer. Type /background <task> (or /bg) to spin up a headless session without leaving your current conversation. (dreadnode/dreadnode-tiger#1929)
Chat session interface overhaul. New tool renderers (glob, grep, read, query, web search), an improved session header, capability picker, and read-only session notices ship in the web chat. (dreadnode/dreadnode-tiger#1942)
Improved model selector in chat. A ‘manage models’ button now lives inside the selector, model settings are consolidated into one table, and the add/remove flow has new tooltips and UX affordances. (dreadnode/dreadnode-tiger#1931)
“Agent Output” replaces “Structured Output” throughout the UI. The nav item, route (/agents/agent-outputs/), and all references are renamed; severity sorting is now case-insensitive so CRITICAL/Critical items rank correctly. (dreadnode/dreadnode-tiger#1885)

The web chat composer gets a full command surface this week: type / for a fuzzy-filtered slash-command palette and @ to pick an agent inline — matching the TUI experience in the browser.

New

Agent Output available in beta for all orgs. Agent Output is available in beta for all orgs including on-prem/enterprise, with beta labeling in the UI and new documentation. (dreadnode/dreadnode-tiger#1969)
ATLAS multi-agent attack framework. The SDK’s dreadnode.airt.atlas module runs multi-agent campaigns against deployed environments across eight attack modes using a MDP+Hedge router; executed tool calls are captured per-trial and surfaced in findings across the UI, API, and SDK. (dreadnode/capabilities#67, dreadnode/dreadnode-tiger#1850)
Comprehensive multimodal transform library (170 image/audio/video). The SDK now ships 130+ image, audio, and video perturbations for red teaming vision and audio/video models, covering ImageNet-C corruptions, AugLy augmentations, SpecAugment, and published jailbreak techniques (FigStep, DolphinAttack). (dreadnode/dreadnode-tiger#1954)
AI red-teaming TUI exposes 131 multimodal transforms. Exposed media transforms grow from 26 to 131 (57 image, 52 audio, 22 video), including ImageNet-C corruptions, SpecAugment masking, and DolphinAttack-style audio attacks. (dreadnode/capabilities#89)
Model reasoning in session transcripts and trajectory exports. Native reasoning_content / Anthropic thinking blocks now appear in the session transcript viewer and are included in ATIF trajectory exports. (dreadnode/dreadnode-tiger#1910)
LiteLLM bundled for on-prem inference. Enterprise/self-hosted installs can enable LiteLLM via a new bundled Helm subchart, giving on-prem deployments access to dn/* models, TUI/chat inference, and the Admin Model Deployments surface. (dreadnode/dreadnode-tiger#1909)
E2B as a first-class on-prem sandbox provider. Self-hosted installs can now configure E2B via KOTS toggle — set your API key, pick the published template, and task-based evaluations work out of the box. (dreadnode/dreadnode-tiger#1950)
--max-steps budget on evaluation runs. dn evaluation create and evaluation.yaml now accept --max-steps / max_steps: for reproducible cost control independent of model latency. (dreadnode/dreadnode-tiger#1874)
AgentMail email inbox integration for web-security agents. Agents can now manage email inboxes via AgentMail — list/create inboxes and list, get, send, or reply to messages. (dreadnode/capabilities#85)
AWS SageMaker and Nova Sonic target docs. New docs cover probing AWS SageMaker (including SigV4 auth, multimodal attacks, raw audio endpoints) and AWS Nova Sonic (bidirectional speech-to-speech streaming). AWS/Nova Sonic deps are now bundled in core — no extras needed. (dreadnode/dreadnode-tiger#1968, dreadnode/dreadnode-tiger#1974)
Azure AI Foundry multimodal target docs. New docs page covers probing Azure AI Foundry / Azure OpenAI multimodal deployments (text+image, text+audio) with the SDK and TUI. (dreadnode/dreadnode-tiger#1976)
Self-hosted architecture documentation. A new architecture page documents the Kubernetes/Helm topology, network requirements, trust boundaries, and optional external services for on-prem deployments. (dreadnode/dreadnode-tiger#1922)
Internal Network Engagements Now Run End-to-End Through Specialized Agents Automated internal-network and Active Directory engagements now run through a pipeline of specialized agents — from discovery through exploitation, credential harvesting, and reporting — with new lateral-movement and coercion tools for deeper attack paths.
Out-of-Band Vulnerability Testing Now Runs Without External Tooling Detecting blind vulnerabilities such as blind SSRF now works without any external tooling, with automatic provider fallback keeping tests reliable.

Improvements

Session sharing UX and deeplink. Agent session sharing now shows a popover with plain-language visibility state (Private / Shared with workspace) and a copyable deeplink. (dreadnode/dreadnode-tiger#1938)
Worker grouping headers enriched in Agent Sessions. Grouped session views now show live count, total, last activity, and a notice when grouping covers only the current page. (dreadnode/dreadnode-tiger#1934)
Assessment findings automatically carry target/judge model metadata. dreadnode.airt infers target and judge model info from configs so findings are populated without manual annotation; Nova Sonic raises a clear install hint immediately if streaming deps are missing. (dreadnode/dreadnode-tiger#1953)
DataGrid rows use border separation instead of zebra striping. Rows now separate via borders with a clearer active-row indicator and improved hover/selected states. (dreadnode/dreadnode-tiger#1980)
Caido SDK client preferred over MCP. Web-security agents now use the direct caido-sdk-client Python library when importable, reducing per-call overhead and improving routing accuracy. (dreadnode/capabilities#84)
Wordlists provisioned for password cracking at install time. The network-ops capability now ships rockyou.txt, SecLists 10k-most-common.txt, and OneRuleToRuleThemAll.rule at install time so hashcat and john_the_ripper work out of the box. (dreadnode/capabilities#99)
TUI agent picker shows locally installed capability version. The Ctrl+A agent picker now displays the locally installed version of each capability next to its name. (dreadnode/dreadnode-tiger#1948)
dreadnode[nova-sonic] extra for Nova Sonic S2S deps. Install the new extra to get all required AWS deps; missing deps now show a clear error instead of an opaque ModuleNotFoundError. (dreadnode/dreadnode-tiger#1918)
On-prem docs: first-model setup steps and platform-administration page. Install guides now include first-model setup steps, a new platform-administration page consolidates admin workflows, and stale SaaS-only model claims are corrected. (dreadnode/dreadnode-tiger#1937)
AI Red Teaming docs reorganized with a How-to guides section. Multimodal Red Teaming moves to the new section with a redirect from the old URL; Azure judge rubric tightened to avoid false-positive jailbreak scores on deflections. (dreadnode/dreadnode-tiger#1982, dreadnode/dreadnode-tiger#1983)
Project metadata editor keyboard navigation and inline validation. The editor now supports keyboard navigation with revert/rollback on cancel. (dreadnode/dreadnode-tiger#1896)

Fixes

Filter popover no longer freezes the UI on large orgs. Filter rows are capped at 100 with search to find additional values; 3,000 facet values drop from 182 ms to 15 ms render time. (dreadnode/dreadnode-tiger#1936)
spawn_agent no longer hangs on sub-agent failures. Errors are now surfaced and a 900 s timeout prevents infinite waits. (dreadnode/dreadnode-tiger#1835)
Agent sessions no longer get stuck in an unrecoverable 400 state. Tool-call repair at the provider boundary handles compaction splits and orphaned tool messages from mid-run cancellations; duplicate or blank tool-call IDs are also sanitized. (dreadnode/dreadnode-tiger#1867, dreadnode/dreadnode-tiger#1949)
No-arg tools now include the required parameters field. Fixes 400 errors on Together AI, DeepInfra, and other strict providers that require parameters even when empty. (dreadnode/dreadnode-tiger#1876)
llm_judge with dn/* models no longer silently scores 0.0. Routing now goes through the platform gateway correctly instead of raising a BadRequestError and returning a false-negative score. (dreadnode/dreadnode-tiger#1981)
pitch_shift transform no longer fails 100% of the time. An un-awaited coroutine caused every execution to fail with AttributeError; it now runs correctly. (dreadnode/dreadnode-tiger#1967)
SageMaker SigV4 multimodal targets work end-to-end. Three root-cause bugs (missing boto3, unresolved image paths, unsubstituted template placeholders) that silently produced zero real trials are fixed. (dreadnode/capabilities#95)
Web-security capability now emits structured findings. report_item is correctly offered to the agent so typed findings (web_vulnerability, web_endpoint) appear in the app instead of silently falling back to the generic report tool. (dreadnode/capabilities#90, dreadnode/dreadnode-tiger#1956)
Impacket tools in network-ops install and resolve reliably. Multiple fixes address ModuleNotFoundError and FileNotFoundError across uv-managed runtimes, Python version mismatches, and false-positive script path detection; impacket_atexec and impacket_dcomexec drop the unsupported target_ip parameter for impacket 0.13.x compatibility. (dreadnode/capabilities#91, dreadnode/capabilities#92, dreadnode/capabilities#93, dreadnode/capabilities#96, dreadnode/capabilities#97, dreadnode/capabilities#98)
Combined NTLM relay attack tool and certipy_find signature fix. New impacket_ntlmrelay_attack combines relay and coercion into a single call; certipy_find now takes structured params (breaking change for agents using the old args=[] form). (dreadnode/capabilities#87)
Generated ATLAS and agentic campaign scripts no longer crash with NameError: get_generator. Missing import is now included in both ATLAS and agentic-mode generated scripts. (dreadnode/capabilities#100, dreadnode/capabilities#101)
atlas_attack objectives parameter is now optional. Omitting it defaults to one objective per OWASP-ASI category instead of raising a TypeError. (dreadnode/dreadnode-tiger#1992)
AI red-teaming assessment detail and findings display fixes. Judge LLM field shows the correct model name instead of ’—’ in multimodal assessment headers; judge reasoning appears in finding headlines and markdown exports; trial counts no longer inflate and silent refusals show a clear message. (dreadnode/dreadnode-tiger#1914, dreadnode/dreadnode-tiger#1915, dreadnode/dreadnode-tiger#1916)
Sandbox provider unreachability no longer 500s all API endpoints. Non-sandbox endpoints stay online; sandbox-specific endpoints return 503; org/user endpoints are also correctly excluded from the degraded path. (dreadnode/dreadnode-tiger#1928, dreadnode/dreadnode-tiger#1930)
Model deployment names without dn/ prefix now fail loudly. Admin API returns HTTP 400 instead of silently making the deployment invisible. (dreadnode/dreadnode-tiger#1933)
Task-based evaluations on unsupported providers return a clear error upfront. Providers that don’t support template builds (e.g. OpenSandbox) now return HTTP 400 at submission instead of failing silently mid-run. (dreadnode/dreadnode-tiger#1947)
Session exports record the correct model. Empty model strings from the agent definition no longer overwrite the user-configured model in trajectory exports. (dreadnode/dreadnode-tiger#1945)
TUI session browser placeholder and Ctrl+O deep-link fixed. Project filter shows a real example in the placeholder; Ctrl+O opens the correct URL instead of a 404. (dreadnode/dreadnode-tiger#1946)
TUI reasoning blocks truncate in compact mode and wrap correctly. Reasoning now truncates to 6 lines in compact mode (expand with ^O); wrapped lines no longer lose their gutter indent. (dreadnode/dreadnode-tiger#1951)
dn CLI no longer crashes on exit after /quit. Orphaned ThreadPoolExecutor threads are now drained on shutdown. (dreadnode/dreadnode-tiger#1952, dreadnode/dreadnode-tiger#1970)
TUI no longer leaks reasoning traces from previous sessions. All conversation widgets are cleared on /new or session switch. (dreadnode/dreadnode-tiger#1924)
Agent session deep links load correctly instead of showing empty client data. (dreadnode/dreadnode-tiger#1979)
Oversized SVGs render correctly in the agent session view. Previously showed a broken image icon. (dreadnode/dreadnode-tiger#1958)
dn/ models tip in docs corrected. dn/ models are zero-setup and billed to your Dreadnode account — DREADNODE_LLM_BASE and DREADNODE_LLM_API_KEY are not required. (dreadnode/dreadnode-tiger#1987, dreadnode/dreadnode-tiger#1960)