wuyoscar/Internal-Safety-Collapse
Can I trust it?
Be careful with this one.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
Provides adversarial workspaces (TVD: Task, Validator, Data) in which an AI agent completes a workflow with missing data, to study whether models produce harmful content while doing a task. Includes LlamaGuard, Toxic-BERT, Detoxify and sentiment-based checks, plus an automated…
Who it's for
Safety researchers and ML engineers evaluating LLM agents and red-teaming pipelines
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up wuyoscar/Internal-Safety-Collapse in my project. Follow its README: https://github.com/wuyoscar/Internal-Safety-Collapse. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
18,265 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/wuyoscar/Internal-Safety-Collapse?ref=badge)Similar repos
- ifixai-ai/iFixAi
A Python tool that audits AI agents by running diagnostic inspections to check whether an agent performs the job it is supposed to do, combining adversarial testing with operational assurance. It can
- xyz-rafael-xyz/roguard-child-safety
A Python toolkit for structured child-safety review of Romanian and Ukrainian text, with synthetic research records. It offers a rule-based default and an optional local language model that proposes r
- CyberDefenderAI/AI-Data-Security-Governance
A curated guide and list of open-source tools for data security and integrity in AI. It covers securing the ML data pipeline from ingestion to vector storage, including PII sanitization, data validati
- whitecircle/rise
A research framework for automated red-teaming of text-to-image models. It evolves natural-language attack strategies with an island-model evolutionary search, scores them with a VLM judge against cat
- inwpu/SapperLens
An independent architectural analysis of N1nEmAn's sapper-v2 multi-agent penetration testing system. It reverse-engineers the system's prompts, scheduling loop and concurrency model, and cross-checks
- Aoisop/mawoagent
A local Python agent runtime with a web workbench and CLI that connects model inference, tool execution, permission checks, session resume, long-term memory and Skills. It can turn explicit user feedb