Vigil
Vigil is a compact classifier designed to run directly on laptops, desktops,
and other endpoint devices. It scans complete AI agent skill packages, including
instructions and supporting files, to identify credential theft, data
exfiltration, unsafe execution, persistence, and other harmful behavior before
a skill is trusted.
Model
- Format: ONNX
- Family: hashed word/character linear classifier
- Input:
features (65,552 features produced by Vigil's preprocessing contract)
- Output: uncalibrated maliciousness score
- Recommended threshold:
0.0000019818544387817383
- Model size: 262,828 bytes
The repository includes the model weights, complete runtime source, prebuilt
runtimes for supported devices, and a local browser scanner.
Getting started
Install Git and Python 3.10 or newer, then run:
1git clone https://huggingface.co/turenlabs/Vigil
2cd Vigil
3python3 tools/local-harness/server.py
On Windows, use:
1git clone https://huggingface.co/turenlabs/Vigil
2cd Vigil
3python tools/local-harness/server.py
The launcher detects the device, installs the matching runtime from this
repository, verifies its SHA-256 hash, starts the scanner, and opens the browser.
Choose a skill folder and select Scan package. Skill files are staged
temporarily and are never executed.
Supported devices are macOS Apple Silicon, Linux AMD64 and ARM64, and Windows
AMD64 and ARM64. See
tools/local-harness for
harness details,
runtime for prebuilt packages, and
source for the complete runtime source.
Evaluation
- F1:
0.9000
- Precision:
0.8874
- Recall:
0.9130
Limitations
The output is a ranking score, not a calibrated probability. Vigil can produce
false positives and false negatives and should be used as one layer of skill
review, not as a sandbox or a guarantee of safety.
Training data is not included in this release.
License:
OpenMDW-1.1. See
LICENSE.
Citation
1@misc{bowyer2026vigil,
2 author = {Tom Bowyer},
3 title = {Vigil: A Compact Classifier for Malicious AI Agent Skills},
4 year = {2026},
5 organization = {Turen Labs, Inc.},
6 url = {https://huggingface.co/turenlabs/Vigil}
7}
References
- Wenbo Guo, Wei Zeng, Chengwei Liu, Xiaojun Jia, Yijia Xu, Lei Tang,
Yong Fang, and Yang Liu. MalSkillBench: A Runtime-Verified Benchmark of
Malicious Agent Skills. arXiv:2606.07131,
2026.
