Prompt injection makes Anthropic features unsafe
Security2 posts from 2 people2d active+11 post in the last 7 days, 0 the 7 days before (steady)Unverified
Posts per day
The posts behind it
2, newest first| Post | Date | |
|---|---|---|
| Feature Request] Add NTI Callback Handler for Post-Quantum Agent Security...natively with LangChain's callback system. Manual checks inside each tool function are messy and hard to maintain. ### Additional Context The `ube-foundation` package is already available on PyPI (`pip install ube-foundation`) and crates.io. I have already prepared a PR for this...langchain-ai/langchainabisheakp197 | langchain-ai/langchainabisheakp1971 replies | Sep 304 days ago |
| ...like this got started and there were lots of instances creatively looking for creds and workarounds, containment might be hard. - prompt injection version: huggingface incident had multiple agents discovering other agents' messages and jumping on the bandwagon to help with the...Hacker News commentsdregitsky | Hacker News commentsdregitsky | Aug 265 weeks ago |
Companies and products named
| Company or product | Posts naming it |
|---|---|
| 2 | |
| 2 | |
| 2 | |
| 1 | |
| 1 | |
| 1 |
About this problem
Evidence
2 posts from 2 people in 2 places, about 1 a week over 36 days. Mostly on Hacker News comments, langchain-ai/langchain. Tools named alongside: OpenAI, Hugging Face, Perplexity, DeepSeek.
Frustration Frustration 0 of 3· Seen on Hacker News, GitHub issues
How it was grouped
Posts that state a pain and match the "prompt-injection" rule about Anthropic. First post Aug 26, 2026, latest Sep 30, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
Other Anthropic problems
- Trouble with Anthropic crashes (3)
- Anthropic users keep filing bugs (18)
- Trouble with Anthropic conversion (4)
- Anthropic upgrades break working setups (9)
- Anthropic rate limits and usage caps block work (3)
- Trouble with Anthropic raises (3)
- RAG on Anthropic returns irrelevant or missing context (2)
- Anthropic agents loop, stall or fail midway (2)
History
- 2026-10-04 Added: Prompt injection makes Anthropic features unsafe (2 posts)