M1 prompt-injection slide deck#2
Open
kkmookhey wants to merge 1 commit into
Open
Conversation
Crown-jewel module deck — denser than M0 by design. Installs the course's core mental model: no boundary between instructions and data. Covers the root cause, direct vs indirect, Halo's L0 vulnerable prompt assembly, the honeytoken objective, a techniques toolbox, obfuscation (P4RS3LT0NGV3), the two guards (prompt hardening + input filter), the vulnerable/secure diff, and the honest "hardening raises cost, doesn't close the channel" takeaway. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
M1-prompt-injection/slides/m1.md— the crown-jewel deck.Deliberately denser than M0 (which is a warm-up): real technical content on the
instruction/data root cause, direct vs indirect, the vulnerable L0 prompt
assembly, the honeytoken exercise, a techniques toolbox, obfuscation, and the
two-guard Secure phase with an honest "no complete fix" takeaway.
Render via Claude Design +
_templates/slide-brief.md→m1.pptx.🤖 Generated with Claude Code