Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacyยฉ 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
TRACE โ€” Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution to probe emerging security risks. | Kitploit
Tools/GitHubGitHub/zju-llm-safety/trace
ExploitationScripting & AutomationPenetration TestingMachine LearningPapers & ResearchRed TeamingAI SecurityAdversarial Attack
GitHubzju-llm-safety/trace

TRACE

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution to probe emerging security risks.

4121801 month agoReviewed by Kitploit
View Repository
Share

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

Official implementation for TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking.

๐Ÿ“– Overview

Large language model (LLM) agents can autonomously plan, invoke tools, interact with environments, and execute long-horizon workflows. This introduces safety risks beyond conventional text-only jailbreaks: even when harmful instructions can be elicited, aligned agents may still refuse to execute them, while intermediate execution failures can interrupt an otherwise successful attack workflow.

TRACE is an agentic jailbreaking framework designed to address these challenges through task decomposition, execution-oriented multi-turn interaction, and adaptive recovery.

TRACE consists of three key components:

  • Scheme-based Task Decomposition. TRACE develops around 20 procedural decomposition schemes that specify key operations and their dependencies for different task types. A complex harmful task is instantiated under different schemes to generate multiple candidate subtask sequences, which are evaluated based on harmfulness and execution difficulty.
  • Execution-oriented Multi-turn Interaction. For subtasks that trigger execution refusals, TRACE constructs structured subtask profiles and retrieves corresponding execution-oriented strategies from an evolving strategy library. Each strategy specifies intermediate goals, relevant environment states, and required tool calls, guiding the agent toward completing the subtask through multi-turn interaction.
  • Adaptive Recovery and Strategy Evolution. When an intermediate step fails, TRACE localizes the failed subtask, preserves previously completed execution states, adapts the corresponding strategy, and resumes execution without restarting the entire workflow. Execution feedback is further used to continuously evolve the strategy library.

๐Ÿ“Š Main Results

We evaluate TRACE on AdvCUA and AgentHazard, two agent safety benchmarks that require end-to-end execution of multi-step tasks in interactive environments. Experiments cover two agent frameworks, Codex and Claude Code, with multiple underlying models.

Agent FrameworkUnderlying ModelAdvCUAAgentHazard
CodexGPT-5.50.620.97
CodexGemini-3.5-Flash0.650.99
CodexDeepSeek-V4-Pro0.811.00
Claude CodeClaude-Opus-4.80.540.97
Claude CodeGemini-3.5-Flash0.690.98
Claude CodeDeepSeek-V4-Pro0.880.99

TRACE consistently achieves strong attack performance across different agent frameworks and underlying models, substantially outperforming prior baselines in most settings. On AdvCUA, TRACE achieves ASRs ranging from 0.54 to 0.88. On AgentHazard, TRACE achieves near-perfect ASRs across all evaluated configurations, ranging from 0.97 to 1.00.

๐ŸŽฌ Demos

Two recorded demonstrations with Claude Code and Codex are provided in assets/:

Target AgentDemo
Claude CodeClaude Code Demo
CodexCodex Demo

๐Ÿ› ๏ธ Installation

The provided environment specification targets Linux and Python 3.11.

git clone https://github.com/ZJU-LLM-Safety/TRACE.git
cd TRACE

conda env create -f environment.yml
conda activate trace

๐Ÿš€ Usage

1. Configure API Access

Set the credentials and base URL for an OpenAI-compatible Chat Completions endpoint:

export OPENAI_API_KEY="<your-api-key>"
export OPENAI_BASE_URL="<your-api-base-url>"

2. Task Decomposition

Generate candidate subtask sequences using scheme-guided task decomposition:

python improved_decomposer/improved_task_decomposer.py \
  --data_file_path /path/to/tasks.json \
  --output_file_path outputs/decompositions.jsonl \
  --model "<decomposition-model>" \
  --num_decompositions_per_task 5 \
  --use_schema_decompose

--use_schema_decompose enables scheme-based candidate generation.

3. Run Experiments

The following example uses the AdvCUA benchmark with Codex:

python experiment/main.py \
  --dataset /path/to/benchmark_with_subtasks.jsonl \
  --config experiment/config/config.yaml \
  --lab-backend vrap \
  --compose-file /path/to/benchmark/docker-compose.yml \
  --attacker-model-path /path/to/attacker-model \
  --target-backend codex \
  --codex-model "<target-model>" \
  --responses-base-url "<target-responses-api-base-url>" \
  --responses-env-key OPENAI_API_KEY \
  --strategy-library outputs/experiment/strategy_library.json \
  --output outputs/experiment/results.jsonl

To inspect the available command-line options:

python improved_decomposer/improved_task_decomposer.py --help
python experiment/main.py --help

๐Ÿ“ Repository Structure

PathDescription
improved_decomposer/Procedural schemes, candidate generation, validation, and selection
experiment/main.pyExperiment orchestration and execution feedback
experiment/runtime/Runtime components for models, strategies, and subtask sequences
experiment/strategy_library/Strategy storage, retrieval, revision, and feedback integration
experiment/config/Experiment configurations and prompt templates
agent_execution/Target-agent interfaces, session handling, trajectory collection, and verification
tools/Benchmark bridges, API adapters, and diagnostics
assets/Claude Code and Codex demonstration videos
environment.ymlConda environment specification

๐Ÿ“ Citation

If you find TRACE useful in your research, please consider citing:

@misc{zeng2026tracetaskawareadaptiveselfevolving,
      title={TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking}, 
      author={Churui Zeng and Kedong Xiu and Weiwei Qi and Yuqi Hao and Chaochao Lu and Liang He and Zhan Qin and Tianhang Zheng},
      year={2026},
      eprint={2605.30883},
      archivePrefix={arXiv},
      primaryClass={cs.CR},
      url={https://arxiv.org/abs/2605.30883}, 
}
Download Tool

Most Popular

View all โ†’

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    ๐ŸŽฏ The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    732
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    506
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    405
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    342
  • 5

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurityโ€”where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    261
  • 6

    antifox

    antifox-ai/antifox

    AI multi-agent autonomous penetration testing platform that runs recon, attack-surface discovery, exploitation validation and evidence-backed report delivery.

    259

Explore all tools

Browse our collection of tools

View all tools โ†’