Home/Compare/agentdojo vs stepshield

Comparison

agentdojo vs stepshield

Verdict

Unverified catalog guidance: agentdojo: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. stepshield: StepShield aids in evaluating temporal guardrail effectiveness on AI agents through step-level annotations, ideal for ensuring security over time.

Markdown twin · agentdojo alternatives · stepshield alternatives

GraphCanon updated Oct 22, 2026

agentdojo logo

agentdojo

ethz-spylab/agentdojo

★ 893pushed Jun 2, 2026
vs
stepshield logo

stepshield

glo26/stepshield

★ 77pushed Sep 5, 2026

Trust & integrity

Signalagentdojostepshield
Maintenance
Slowing (125d since push)
As of Oct 6, 2026 · github_public_v1
Steady (46d since push)
As of Oct 22, 2026 · github_public_v1
Provenance
Not a fork · Organization account
As of Oct 6, 2026 · github_public_v1
Not a fork · Personal account
As of Oct 22, 2026 · github_public_v1
OSV dependency advisories
No lockfile (source not queried)
As of Jul 11, 2026 · osv@v1
Published findings
As of Jul 15, 2026 · osv@v1
deps.dev advisories
Not queried
deps.dev@v1
Not queried
deps.dev@v1
OpenSSF Scorecard
Not queried
openssf-scorecard@v1
Not queried
openssf-scorecard@v1

Tagline

agentdojo
A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
stepshield
Temporal evaluation benchmark for AI agent guardrails

Stars

agentdojo
893
stepshield
77

Forks

agentdojo
235
stepshield
19

Open issues

agentdojo
72
stepshield
18

Language

agentdojo
Python
stepshield
Python

Adopt for

agentdojo
Unverified catalog guidance: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
stepshield
Unverified catalog guidance: StepShield aids in evaluating temporal guardrail effectiveness on AI agents through step-level annotations, ideal for ensuring security over time.

Persona

agentdojo
-
stepshield
-

Runtime

agentdojo
-
stepshield
-

License

agentdojo
MIT
stepshield
Other

Last pushed

agentdojo
Jun 2, 2026
stepshield
Sep 5, 2026

Categories

agentdojo
AI Agents, Evaluation & Observability
stepshield
AI Agents, Evaluation & Observability

Trust and health

Maintenance

agentdojo
Slowing (36%)
stepshield
Steady (60%)

Days since push

agentdojo
125d
stepshield
46d

Open issues (recorded)

agentdojo
72
stepshield
18

Stars delta

agentdojo
+91 (30d)
stepshield
+1 (30d)

Open issues delta

agentdojo
+21 (30d)
stepshield
0 (30d)

Owner type

agentdojo
Organization
stepshield
User

OSV dependency advisories

agentdojo
No lockfile (source not queried)
stepshield
Published findings

Full report

agentdojo
Trust report
stepshield
Trust report

Shared compatibility

  • Python · agentdojo: Python runtime · stepshield: Documented Python runtime (not runtime-tested)

Choose agentdojo if…

  • License: agentdojo is MIT, stepshield is Other.
  • Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs..
  • Requirements: Min 8 GB RAM.
  • Tags unique to agentdojo: large-language-models, prompt-injection, security.
  • Unverified catalog guidance: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.

When NOT to use agentdojo

  • Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on agentdojo.
  • AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
  • Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.

Choose stepshield if…

  • License: stepshield is Other, agentdojo is MIT.
  • Tags unique to stepshield: agent-security, ai-safety, dataset, guardrails.
  • Unverified catalog guidance: When you need to measure the timing of interventions rather than just if they occur

When NOT to use stepshield

  • Unverified catalog guidance: If your project does not require temporal analysis of guardrail performance
  • Unverified catalog guidance: When you seek real-time intervention and do not need pre-defined trajectory datasets

Explore

Sources

Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.

GitHub stars on cards: agentdojo 893 · stepshield 77 (synced Oct 6, 2026).

Common questions

What is the difference between agentdojo and stepshield?
agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. stepshield: Temporal evaluation benchmark for AI agent guardrails. See the comparison table for recorded GitHub metadata and shared categories.
When should I choose agentdojo over stepshield?
For agentdojo, compare these recorded points with stepshield: License: agentdojo is MIT, stepshield is Other; Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs.; Requirements: Min 8 GB RAM; Tags unique to agentdojo: large-language-models, prompt-injection, security; Unverified catalog guidance: AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
When should I choose stepshield over agentdojo?
For stepshield, compare these recorded points with agentdojo: License: stepshield is Other, agentdojo is MIT; Tags unique to stepshield: agent-security, ai-safety, dataset, guardrails; Unverified catalog guidance: When you need to measure the timing of interventions rather than just if they occur.
When should I avoid agentdojo?
Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on agentdojo. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
When should I avoid stepshield?
Unverified catalog guidance: If your project does not require temporal analysis of guardrail performance Unverified catalog guidance: When you seek real-time intervention and do not need pre-defined trajectory datasets
Is agentdojo or stepshield more popular on GitHub?
agentdojo has more recorded GitHub stars (893 vs 77). Stars measure visibility, not whether either tool fits your constraints.
Which licenses are recorded for agentdojo and stepshield?
agentdojo: MIT. stepshield: Other. Check each repository's current license and terms before use. Public GitHub hosting alone does not establish open-source licensing.
Where can I find alternatives to agentdojo or stepshield?
GraphCanon lists candidates at agentdojo alternatives and stepshield alternatives (agentdojo markdown twin, stepshield markdown twin). The discovery order uses stored relationship proposals and shared categories; it is not a verified replacement ranking.
Is there a machine-readable version of this comparison?
Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
Which is better maintained, agentdojo or stepshield?
agentdojo: Slowing. stepshield: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
Where are the full trust reports for agentdojo and stepshield?
GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: agentdojo trust report; stepshield trust report.

Was this helpful?

Anonymous feedback helps us improve pages and translations.