Lurkr — pre-deployment scanner for risky AI agent capabilities. Static. Offline. Redacted.
Project description
Lurkr
Find what your agent can touch before you deploy it.
Lurkr is a pre-deployment, static, local-only scanner that flags risky AI-agent and GitHub-workflow capability issues. No telemetry, no network calls, no project code execution. Reports are redacted by default.
Quick Start
pip install lurkr
lurkr scan --path . --output report.json
cat report.json
To fail CI when findings meet a threshold:
lurkr scan --path . --output report.json --fail-on high
Current Scope
v0.2 includes ten high-severity rules across GitHub workflows, agent manifests, identity files, and bounded Python agent-source analysis.
Lurkr is read-only, offline, telemetry-free, and static-only. It does not modify scanned files, execute project code, or send repository data over the network.
Links
- Repository: https://github.com/agentveil-protocol/lurkr
- Documentation: https://github.com/agentveil-protocol/lurkr#readme
- Issues: https://github.com/agentveil-protocol/lurkr/issues
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file lurkr-0.2.0.tar.gz.
File metadata
- Download URL: lurkr-0.2.0.tar.gz
- Upload date:
- Size: 40.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
88947be16da85fdb5d1f030ee47b658f37982ca02c18297e546276b0370ab0cb
|
|
| MD5 |
0fd7c1ea7fbbdff54a22199ead9f9eeb
|
|
| BLAKE2b-256 |
20de993166ef6a4442af1d22b3778e32fb9c30ee5c598ea2a6f76ada58d1bb11
|
File details
Details for the file lurkr-0.2.0-py3-none-any.whl.
File metadata
- Download URL: lurkr-0.2.0-py3-none-any.whl
- Upload date:
- Size: 21.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
83b0b381e10a7d9bfa44f90ab8d1084a54136ec681e02e79c53eea305c931f0f
|
|
| MD5 |
4cff15fa9df0158e776a38ecf7c3c0f5
|
|
| BLAKE2b-256 |
c882ebbff2b5784bda1eb6be6eca06f409b2eb16c2473870c0db21b8cdc5b465
|
