security(#299): neutralize prompt-injection in untrusted inbound content#309
Draft
nolanmak wants to merge 1 commit into
Draft
security(#299): neutralize prompt-injection in untrusted inbound content#309nolanmak wants to merge 1 commit into
nolanmak wants to merge 1 commit into
Conversation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #299.
Neutralizes prompt-injection via untrusted inbound content. Email
from/subject/body, thread-history bodies, and GitHub issue/notification title+body were interpolated raw into reasoner prompts inside pseudo-XML tags with no escaping — a crafted body could forge a</email>close tag plus injected instructions and steer a tool-holding model.sanitize_untrusted()(entity-encodes&/</>) applied to every untrusted field at all interpolation sites inprompt.rs(triage,draft,code_mode,redraft,format_thread_history) andingest.rs. GitHub channel inherits this transitively (nochannel-githubedit needed).Verification:
cargo check -p augmentagent-channel-coreclean;cargo test -p augmentagent-channel-core= 203 lib + 6 integration tests pass, incl. 3 new injection regression tests.🤖 swarm-authored, human-review-required (draft).