Skip to content

Shadow-LLM/failure-cases

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 

Repository files navigation

failure-cases

Public archive of LLM and AI agent failure cases. Backend for shadow-llm.com.

This repo is content, not code. Every issue in this repo is one failure case. Comments on the issue are the discussion thread. 👍 reactions are upvotes. The site at shadow-llm.com renders them with a custom front-end.

Submit a case

  1. Read the disclosure policy — please do not file undisclosed 0-days.
  2. Open a new issue and fill in the structured form.
  3. Your case appears on shadow-llm.com after the next site rebuild (auto-triggered, ~1 min).

What's a good case?

  • Specific: a single failure mode, not a survey
  • Reproducible: someone else can re-run it (or you say so honestly)
  • Cited threat model: who is the realistic attacker / affected party?
  • Sanitized: no PII, no operational uplift beyond what's needed to demonstrate

What we collect

hallucination, jailbreak, prompt-injection, agent-loop, tool-misuse, over-refusal, sycophancy, alignment, destructive-action, multimodal, and the long tail of weird behavior that doesn't have a name yet.

What we don't collect

Attack tutorials with no defensive value. Zero-days before responsible disclosure. Content targeting individuals. See DISCLOSURE.md.

License

Case content (issue bodies, comments) is contributed under CC-BY-4.0 unless the author specifies otherwise. By submitting you grant a license to redistribute with attribution.

Related


Shadow-LLM-Guardians — watchful protectors in the age of AI.

About

Community archive of LLM and AI agent failure cases. Site: https://shadow-llm.com

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors