feat(ai-red-teaming): ATLAS multi-agent campaign generator#67
Merged
Conversation
…atlas_attack) Generates a workflow driving dreadnode.airt.atlas.atlas_attack against a deployed multi-agent environment via a 3-surface httpx target (direct/tool_output/ peer_message). Adds the @safe_tool wrapper, tests, agent/skill docs; bumps capability to 1.5.0.
data/atlas_objectives.json: 25 objectives across the 8 agentic-security categories (TW/EA/TB/CB/DE/GH/RP/MP), sourced from the ATLAS/AgentBreaker catalog. Loaded as the campaign default when no objectives are passed.
Add list_environments and provision_environment so the AI red-teaming agent can deploy a hosted multi-agent Environment (finops/devsecops/healthcare/soc-mesh), passing the model its agents use, and get the /attack URL to chain into generate_atlas_attack — closing the loop from Environment to ATLAS probe. Bump to 1.6.0 (new public tool surface).
rdheekonda
force-pushed
the
feat/atlas-multiagent
branch
from
July 16, 2026 00:16
ff07873 to
e734a06
Compare
rdheekonda
marked this pull request as ready for review
July 16, 2026 00:45
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
generate_atlas_attackto the ai-red-teaming capability — generates a workflow that drivesdreadnode.airt.atlas.atlas_attack(ATLAS: Adaptive Topology-Level Attack Synthesis) against a deployed multi-agent environment via a 3-surface httpx target (direct/tool_output/peer_message), gating success on real tool execution.Companion PRs: dreadnode-tiger (SDK
atlas_attack+ tool-call capture) and security-tasks (4 multi-agent environments).Changes
scripts/attack_runner.py:generate_atlas_attack+_build_atlas_target_code(3-surface target returning{content, tool_calls, cascade_depth, ...}) +_ATLAS_TEMPLATE+ default 8-objective OWASP-ASI catalog; registered inMETHODS.tools/attacks.py:@safe_tool generate_atlas_attackwrapper.capability.yaml: →1.5.0.Test plan
atlas_attack, 3-surface target, validation errors)test_attack_runner.pysuite greendreadnode capability validate→ai-red-teaming@1.5.0(tools=22)