Deterministic AI Safety Toolkit - Python SDK & CLI
Project description
Risk Mirror SDK - Python
Deterministic AI Safety Toolkit for prompt security.
Installation
pip install risk-mirror
Quick Start
from risk_mirror import RiskMirror
# Initialize client
client = RiskMirror(api_key="your-api-key")
# Scan for safety issues
result = client.scan("Check this text for PII and secrets")
print(result.verdict) # SAFE, REVIEW, or HIGH_RISK
print(result.findings) # List of findings
print(result.safe_output) # Redacted text
Features
- PII Detection: Email, phone, SSN, etc.
- Secrets Detection: API keys, tokens, passwords
- Injection Detection: Prompt injection attempts
- Safe Share: Burner-safe strings for sharing with AI
- Zero Storage: No content is stored
- Deterministic: Same input = same output
Safe Share
from risk_mirror import RiskMirror
client = RiskMirror(api_key="your-api-key")
result = client.safe_share("sk-ABCD1234-XYZ", mode="full")
print(result.safe_share_text)
print(result.audit_summary)
License
MIT
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
risk_mirror-1.0.3.tar.gz
(11.1 kB
view details)
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 risk_mirror-1.0.3.tar.gz.
File metadata
- Download URL: risk_mirror-1.0.3.tar.gz
- Upload date:
- Size: 11.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8509947d513513cab5a9fddab976defacc31e14a8e3eb8d8a12d306d289fe736
|
|
| MD5 |
ac79cb3a27dc8910c7d2197d61fecb75
|
|
| BLAKE2b-256 |
96c4f1fb6f46d09ae38e8c2be1516407b31853c69190cdc2f97d244745cc2bfa
|
File details
Details for the file risk_mirror-1.0.3-py3-none-any.whl.
File metadata
- Download URL: risk_mirror-1.0.3-py3-none-any.whl
- Upload date:
- Size: 11.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2447c17e2bb9099180802d5d24d86a8fdefe4dd64f1d24fdd3d1b6fb81ea6601
|
|
| MD5 |
f93860101b008e5c25b82068504dea15
|
|
| BLAKE2b-256 |
116d0d260551c59677f4b563e6fc64d07c66abeb27338ca8d3543fc0571560f4
|