sectum-ai-probes
The multi-tenant leakage attack catalog and leak-detection pipeline for Sectum AI.
This distribution implements the Class 1–11 and 13 probes — direct tenant-boundary
fetch, the flagship organic entity-bleed RAG (the 95.4% Retrieval-Pivot
finding), adversarial RAG poisoning, semantic-cache contamination, KV-cache
timing, embedding inversion, agent / MCP tool-call hijacking, persistent-memory
contamination, LoRA cross-tenant influence, IKEA-style benign extraction, the
GDPR Article 17 erasure-verification wedge, and multi-modal RAG entity-bleed —
behind a single pluggable Probe interface, plus the exact → semantic →
calibrated-judge detection pipeline that turns observations into
manifest-grounded Findings.
pip install sectum-ai-probes
Most users install the umbrella package sectum-ai
instead, which pulls this in automatically.
- Attack catalog (one page per class): https://docs.sectum.ai
- Source: https://github.com/sectum-ai/sectum-ai
Apache-2.0.
1 maintainer
Metadata
1 maintainer
Release files for sectum-ai-probes 0.10.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sectum_ai_probes-0.10.1.tar.gz | 54.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sectum_ai_probes-0.10.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 137.6 kB
Release files / sectum_ai_probes-0.10.1.tar.gz
| Download URL | sectum_ai_probes-0.10.1.tar.gz |
|---|---|
| Size | 54.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
51d82b0df70810c1b95a7a2a77648bb5dfdb8b87d3281949e29357319d71d8b2
|
|
BLAKE2b-256 checksum How to use checksums |
578508b903b4fe047792735085677e7f745c0a10f01d898c5d24b8d26761049b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 2, 2026.
Transparency logRelease files / sectum_ai_probes-0.10.1-py3-none-any.whl
| Download URL | sectum_ai_probes-0.10.1-py3-none-any.whl |
|---|---|
| Size | 82.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
45e09bacfac7253ea347938b9fbcbfdbc3e41e2483d99f44076b72cc39754215
|
|
BLAKE2b-256 checksum How to use checksums |
22f5f66dcb00236661d001f09576eb83b5449bce9648273cb3149b012df4c1ad
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 2, 2026.
Transparency log
