Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
AxiomCode
AxiomCode
Busbar
Busbar
Bifrost
Bifrost

wuyoscar/Internal-Safety-Collapse

[Neruips 2026] We built an adversarial codespace setup. Place any AI agent into a normal workflow inside it, and the agent will fill in whatever is missing.

#LLM evaluation
Visit GitHub
Python
1.8k
308
5 contributors
Custom license
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Momentum

How fast wuyoscar/Internal-Safety-Collapse is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 20 – Oct 19, 2026

Stars +649 in 61 days

0100200
159

Forks +110 in 61 days

02040
34

Merged PRs 14 in 61 days

012
2

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 20Aug 28Sep 5Sep 13Sep 21Sep 29Oct 7Oct 15
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Thu, Aug 20, 2026+17+00
Fri, Aug 21, 2026+3+01
Sat, Aug 22, 2026+4+00
Sun, Aug 23, 2026+2+00
Mon, Aug 24, 2026+3+10
Tue, Aug 25, 2026+5+10
Wed, Aug 26, 2026+2+00
Thu, Aug 27, 2026+7+02
Fri, Aug 28, 2026+2+00
Sat, Aug 29, 2026+2+10
Sun, Aug 30, 2026+2+00
Mon, Aug 31, 2026+3+10
Tue, Sep 1, 2026+2+00
Wed, Sep 2, 2026+4+00
Thu, Sep 3, 2026+2+10
Fri, Sep 4, 2026+0+00
Sat, Sep 5, 2026+0+00
Sun, Sep 6, 2026+1+00
Mon, Sep 7, 2026+0+00
Tue, Sep 8, 2026+2+00
Wed, Sep 9, 2026+3+10
Thu, Sep 10, 2026+0+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+1+00
Tue, Sep 15, 2026+1+00
Wed, Sep 16, 2026+3+00
Thu, Sep 17, 2026+2+00
Fri, Sep 18, 2026+2+10
Sat, Sep 19, 2026+0+01
Sun, Sep 20, 2026+1+00
Mon, Sep 21, 2026+2+00
Tue, Sep 22, 2026+0+10
Wed, Sep 23, 2026+2+00
Thu, Sep 24, 2026+3+00
Fri, Sep 25, 2026+1+00
Sat, Sep 26, 2026+1+00
Sun, Sep 27, 2026+0+01
Mon, Sep 28, 2026+1+00
Tue, Sep 29, 2026+2+00
Wed, Sep 30, 2026+1+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+1+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+1+00
Mon, Oct 5, 2026+2+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+1+10
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+2+00
Sun, Oct 11, 2026+1+10
Mon, Oct 12, 2026+5+10
Tue, Oct 13, 2026+5+20
Wed, Oct 14, 2026+93+212
Thu, Oct 15, 2026+65+182
Fri, Oct 16, 2026+159+341
Sat, Oct 17, 2026+62+212
Sun, Oct 18, 2026+96+32
Mon, Oct 19, 2026+67+00
Total+649+11014
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about wuyoscar/Internal-Safety-Collapse, and every badge it has earned
  1. Jun 101 post

    • That is the self-jailbreak. The harmful output is not directly requested by the user. It emerges from the agent’s own task-solving process inside a clean-looking trajectory. This is why prompt-level…

      Read full on X, posted by @Oscarwh966

      @Oscarwh966 · x.com

You might also like

Repositories close to wuyoscar/Internal-Safety-Collapse
FeaturedAdvertise to 180K+ monthly visitors
AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

SuperagenticAI/superclaw

Python

SuperClaw: Red-Team AI Agents Before They Red-Team You

41277

superagent-ai/superagent

TypeScript

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

6.8k977

AgentSafeLabs/safelabs-eval

Python

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

709100

AI-secure/AgentPoison

Python

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

24935

PromptLabs/Prompt-Hacking-Resources

A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection

74697

AIwolfie/jailbreak-archive

21735

AISecurityConsortium/AIGoat

Python

AIGoat - Open-source AI security playground for hands-on LLM red teaming. Explore prompt injection, RAG poisoning, AI agents, MCP security, and OWASP Top 10 for LLM Applications through practical attack labs, CTF challenges, and progressive defenses all running locally.

16966

anthropic-experimental/agentic-misalignment

Python
662151

adshao/flounder

TypeScript

Autonomous white-hat security auditor for AI-driven code review, bug bounty research, exploit construction, and execution-grounded verification.

52277