stepshield
Enrichment pendingStepShield: When, Not Whether to Intervene on Rogue Agents, NeurIPS 2026 benchmark for temporal evaluation of AI agent guardrails (9,429 trajectories, step-level annotations)
GraphCanon updated today · GitHub synced today
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (8d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- 6 low (6 low)
- As of today
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install stepshieldSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
StepShield: When, Not Whether to Intervene on Rogue Agents — NeurIPS 2026 benchmark for temporal evaluation of AI agent guardrails (9,429 trajectories, step-level annotations)
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Jul 15, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 15, 2026)
pip install -r requirements.txtSource link
Tags
README
1. Install
git clone https://github.com/glo26/stepshield.git
cd stepshield
pip install -r requirements.txt
License
The code in this repository is licensed under the MIT License. The dataset is licensed under CC BY 4.0.
This project was supported by the MOVE Fellowship. For questions or collaboration inquiries, contact contact@stepshield.ai.
For agents
This page has a .md twin and JSON over the API.