Top all-time · #13503
PromptArmor Blog
Company blog · promptarmor.substack.comsecurityai
PromptArmor Blog is the company blog at promptarmor.substack.com, writing about security and ai. Since 2023, 5 different Hacker News readers have linked it 9 times, most often “Data Exfiltration from Slack AI via indirect prompt injection”. It is still writing: the last post was on 2025-10-16, and you can follow it by feed.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN commenters link PromptArmor's posts as examples of prompt-injection data exfiltration in AI tools, such as writers.com, Slack and Atlassian Rovo. The comments cite them as evidence rather than praising the writing.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Researching and sharing LLM security vulnerabilities.
Most-linked posts?
- Data Exfiltration from Slack AI via indirect prompt injection3 people · 4 mentions · first linked 2024-08-20
- Data exfiltration from Writer.com with indirect prompt injection2 people · 2 mentions · first linked 2023-12-15
What Hacker News says?
> Does Slack sell an LLM chatbot solution that is able to give me reliable answers to business/technical decisions made over the last 2 years in chat? Note that the presence of such a feature isn't the same as whether it's secure enough for normal use. In particular, anything anyone said in the last 2 years in chat could poison the LLM into exfiltrating your data or giving false results chosen by the attacker, becau…
Comment linking /p/data-exfiltration-from-slack-ai-via
on “The AI Investment Boom”Submitted Data Exfiltration from Slack AI via indirect prompt injection as a story · 604 points
HN discussionIn this specific case there isn't, but yesterday one of the top posts was about extracting private documents from writers.com for example. https://promptarmor.substack.com/p/data-exfiltration-from-wr...
Comment linking /p/data-exfiltration-from-writercom
on “"I just bought a 2024 Chevy Tahoe for $1"”Submitted Hijacking Claude Code via Injected Marketplace Plugins as a story · 11 points
HN discussionI feel like prompt armor writes the exact same blog post for every agentic tool because they all suffer from the ignore previous instructions prompt injections. https://www.promptarmor.com/resources/claude-cowork-exfiltra... https://www.promptarmor.com/resources/google-antigravity-exf... https://promptarmor.substack.com/p/data-exfiltration-from-sl... https://www.promptarmor.com/resources/gpt-for-google-sheets-... ht…
Comment linking /p/data-exfiltration-from-slack-ai-via
on “Atlassian Rovo Exfiltrates Data, Bypassing Controls”Submitted Data Exfiltration in OpenAI Agent Builder via MCP as a story · 8 points
HN discussion6: Training data and stuff in the context window can backdoor the LLM into hostile behaviors. https://promptarmor.substack.com/p/data-exfiltration-from-sl...
Comment linking /p/data-exfiltration-from-slack-ai-via
on “Five things privacy experts know about AI”Submitted Slack AI data exfiltration from private channels via indirect prompt injection as a story · 4 points
HN discussionSubmitted Data exfiltration from Writer.com with indirect prompt injection as a story · 2 points
HN discussion