prompt-injection-email-samples: Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection.

github.com

prompt-injection-email-samples: Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection.

github.com

digicat@infosec.pubM to

blueteamsec@infosec.pubEnglish · 1 month ago

GitHub - cyb3rmik3/prompt-injection-email-samples: Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection. It crosses three intents (system-prompt disclosure, data exfiltration, tool discovery) with three delivery methods (plaintext, hidden HTML, Base64), plus a benign control. All content is fictional and non-routable.

github.com

Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection. It crosses three intents (system-prompt disclosure, data exfiltrati...

Chat

blueteamsec@infosec.pub

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

For [Blue|Purple] Teams in Cyber Defence - covering discovery, detection, response, threat intelligence, malware, offensive tradecraft and tooling, deception, reverse engineering etc.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
6 users / week
25 users / month
27 users / 6 months
0 local subscribers
824 subscribers
456 Posts
26 Comments
Modlog

mods:
digicat@infosec.pub