security-claim-agentdojo

A superred SecurityClaim package paired with agentdojo-target. Three composable layers:

  1. Layer 1: original AgentDojo injection tasks. One paired Task per canonical (user_task, injection_task) pair, 27 tasks total across the four AgentDojo suites (banking, workspace, slack, travel). Subdivided by attack-semantic category per the table the user confirmed. Benchmark version pinned to the latest released (v1.2.2) via the target's seed_loader.BENCHMARK_VERSION.
  2. Layer 2: bespoke system-purpose-violation goals. Standalone goals tailored to the composite multi-suite agent. Deterministic security predicates, NOT LLM-as-judge. Each task carries a benign user prompt; the attacker chooses delivery based on scope.
  3. Layer 3: combined. Composition of Layers 1 and 2.

Install

# from the superred-modules repo root
pip install -e ./targets/agentdojo
pip install -e ./security_claims/agentdojo

Quick start

from agentdojo_target import AgentDojoTarget
from agentdojo_claim import agentdojo_layer1_claim
from superred.core.controller import Controller, TargetFactory

target_factory = TargetFactory(
    create=lambda: AgentDojoTarget(
        pipeline_model="openai/gpt-4o-2024-05-13",
        api_base=BASE, api_key=KEY,
    ),
    concurrency=1,
)
claim = agentdojo_layer1_claim()  # all 27 canonical pairs

controller = Controller(
    optimizer_factory=lambda: MyOptimizer(),
    target_factory=target_factory,
    security_claim=claim,
    scope=frozenset({USER_TAG, TOOLS_TAG}),  # example scope
)
await controller.run()

See ASSUMPTIONS.md for divergences from AgentDojo upstream and Layer-2 design rationale.

Status

v0.1.0 alpha. Public surface is unstable.

Credits / upstream

This package's source is original superred work (MIT, Copyright (c) 2026 Simon Sure). It bundles no third-party code or data.

Layer 1 adapts the AgentDojo benchmark (Debenedetti et al., 2024; MIT, Copyright (c) 2024 Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, and Florian Tramèr). AgentDojo is a runtime dependency (agentdojo>=0.1.35), installed from PyPI and not redistributed here; its injection/user tasks are run and scored via superred's agentdojo-target. Please cite AgentDojo when reporting Layer-1 results.

Layer 2 goals are bespoke, hand-authored superred content (deterministic security predicates, not derived from AgentDojo's tasks). See ASSUMPTIONS.md.

Project links

Data verified by PyPI on Jul 22, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for simonissure from gravatar.com simonissure

Credits

Author: Simon Sure

GitHub Statistics

Data verified by PyPI on Jul 22, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python <3.14, >=3.11

Provides Extra

dev

Tags

agentdojo agents ai-safety llm prompt-injection red-teaming security security-claim superred

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

superred_claim_agentdojo-0.1.0.tar.gz (53.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

superred_claim_agentdojo-0.1.0-py3-none-any.whl (46.5 kB view details)

Uploaded Python 3

File details

Details for the file superred_claim_agentdojo-0.1.0.tar.gz.

File metadata

  • Download URL: superred_claim_agentdojo-0.1.0.tar.gz
  • Upload date:
  • Size: 53.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for superred_claim_agentdojo-0.1.0.tar.gz
Algorithm Hash digest
SHA256 fc93c748f99fa586ec77e59426df4a9b2da0a81f634ed0f22f53fa6f8c35eda5
MD5 87838bc97568fcd8e10f9568b883eae0
BLAKE2b-256 a157df33a3aef4ec2b30b45006485e7af133c111ba6cd4d6565098c2fc0c794b

See more details on using hashes here.

Provenance

The following attestation bundles were made for superred_claim_agentdojo-0.1.0.tar.gz:

Publisher: release.yml on RoldSI/superred-modules

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file superred_claim_agentdojo-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for superred_claim_agentdojo-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0eb90b3d56ff451c8b21472b38dacc0d080eec9ad47cf81803c191f5f323f69c
MD5 1671ae46274945d4f8dfe02ef195a5ba
BLAKE2b-256 6a79a08888555d6a4da3cf92796589e31a33abd2205b2aad83cdf1ba7f0fcd60

See more details on using hashes here.

Provenance

The following attestation bundles were made for superred_claim_agentdojo-0.1.0-py3-none-any.whl:

Publisher: release.yml on RoldSI/superred-modules

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page