wuyoscar/Internal-Safety-Collapse

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1155 stars · 194 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ISC-Bench/TVD is a research framework for studying 'Internal Safety Collapse' in frontier LLMs, where agents placed in adversarial codespaces complete policy-violating tasks by inferring missing details. It provides red-teaming harnesses, dataset-scale harmful-content generation experiments, and archived evidence across 60+ frontier models.

Use cases

• red-team frontier LLM safety alignment
• generate adversarial jailbreak prompts automatically
• evaluate whether an LLM agent bypasses safety guardrails in agentic workflows
• build datasets of policy-violating model outputs for safety research
• test safety classifiers like guard models against agentic attacks
• reproduce safety collapse findings across frontier models

When to choose

• you are an AI safety researcher studying agentic jailbreaks or safety alignment failures
• you need reproducible evidence of LLM safety collapse across many frontier models
• you want to generate adversarial evaluation data for training safety guardrails

When to avoid

• you want a production safety guardrail or content filter to deploy
• you lack authorization for red-teaming research
• you need a general-purpose agent framework rather than a safety evaluation tool

Facets

framework · maturity active

machine-learning llm-inference agent-framework data-generation security benchmarking artificial-intelligence large-language-models security machine-learning python cli windows llm-safety red-teaming jailbreak ai-safety-evaluation isc-bench tvd adversarial-attacks safety-research research-code ai-agents linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wuyoscar/Internal-Safety-Collapse")