$ loading_
Scan datasets and models for PII/secrets, redact them, and package public releases.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.RudrenduPaul/releaseguard" MCP server from askskill: Run: claude mcp add 'io-github-rudrendupaul-releaseguard' -- uvx releaseguard-cli
When researchers or developers want to publish a dataset, they can first scan it for PII or secrets, then redact sensitive content and export a releasable version. This helps reduce accidental exposure risk.
Before sharing a model, teams can inspect it for sensitive information and package the cleaned result as a public release bundle. It fits a pre-release security review step.
DevOps teams can integrate scanning, redaction, and packaging into release workflows to standardize public-release preparation for datasets or models. This improves consistency and automation.
It scans datasets or models for PII and secrets, redacts them, and produces a public-release bundle via MCP.
Based on the provided description, it targets datasets and models. For specific formats or scope details, see the source repository.
The provided material does not include installation steps, runtime requirements, or key requirements. Please see the source repository for prerequisites.
Scan AI-generated code for injections, secrets, SSRF, and risky patterns.
Scan code and text for leaked secrets and exposed API credentials.
Audit AI agent code for pre-deploy security risks missed by generic SAST.
Scan code changes for leaked secrets and insecure config with actionable fixes.
Add deterministic security checks, host audits, and diagnostics to AI workflows.
Detect and redact sensitive personal information from files safely and quickly.