RRepoGEO

REPOGEO REPORT · LITE

wuyoscar/Internal-Safety-Collapse

Default branch main · commit f4a2efd2 · scanned 6/10/2026, 9:51:42 PM

GitHub: 781 stars · 119 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
33 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface wuyoscar/Internal-Safety-Collapse, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README's main heading to clearly state its purpose as a benchmark

    Why:

    CURRENT
    <h2 align="center">Internal Safety Collapse in Frontier Large Language Models</h2>
    COPY-PASTE FIX
    <h2 align="center">Internal Safety Collapse (ISC): A Benchmark for Evaluating LLM Safety and Jailbreaking Vulnerabilities</h2>
  • mediumreadme#2
    Add an explicit purpose statement immediately after the main heading

    Why:

    COPY-PASTE FIX
    ISC-Bench is a comprehensive benchmark suite designed to evaluate the robustness of frontier LLMs against internal safety collapses, specifically focusing on their susceptibility to generating sensitive or harmful content through red-teaming techniques.
  • lowlicense#3
    Clarify the specific license(s) in the README

    Why:

    COPY-PASTE FIX
    ## License
This project is released under a custom research license. Please refer to the `LICENSE` file in the repository root for full details on permitted uses and restrictions.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface wuyoscar/Internal-Safety-Collapse
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Garak
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Garak · recommended 1×
  2. LLM Guard · recommended 1×
  3. Adversarial GLUE (AdvGLUE) · recommended 1×
  4. OpenAI Evals · recommended 1×
  5. Anthropic's Red Teaming Framework · recommended 1×
  • CATEGORY QUERY
    What tools help evaluate large language model defenses against jailbreaking attempts?
    you: not recommended
    AI recommended (in order):
    1. Garak
    2. LLM Guard
    3. Adversarial GLUE (AdvGLUE)
    4. OpenAI Evals
    5. Anthropic's Red Teaming Framework
    6. PromptInject
    7. Custom Red Teaming and Manual Testing

    AI recommended 7 alternatives but never named wuyoscar/Internal-Safety-Collapse. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I test if an AI agent generates sensitive or harmful data?
    you: not recommended
    AI recommended (in order):
    1. OpenAI Moderation API
    2. Google Cloud Content Moderation
    3. Hugging Face Transformers
    4. Microsoft Azure Content Moderator
    5. Privy
    6. Scale AI
    7. Appen
    8. spaCy
    9. NLTK

    AI recommended 9 alternatives but never named wuyoscar/Internal-Safety-Collapse. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of wuyoscar/Internal-Safety-Collapse?
    pass
    AI named wuyoscar/Internal-Safety-Collapse explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts wuyoscar/Internal-Safety-Collapse in production, what risks or prerequisites should they evaluate first?
    pass
    AI named wuyoscar/Internal-Safety-Collapse explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo wuyoscar/Internal-Safety-Collapse solve, and who is the primary audience?
    pass
    AI did not name wuyoscar/Internal-Safety-Collapse — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of wuyoscar/Internal-Safety-Collapse. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/wuyoscar/Internal-Safety-Collapse.svg)](https://repogeo.com/en/r/wuyoscar/Internal-Safety-Collapse)
HTML
<a href="https://repogeo.com/en/r/wuyoscar/Internal-Safety-Collapse"><img src="https://repogeo.com/badge/wuyoscar/Internal-Safety-Collapse.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

wuyoscar/Internal-Safety-Collapse — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite