security: sanitize web content to prevent prompt injection (#248)#342
Open
Shraman123 wants to merge 1 commit into
Open
security: sanitize web content to prevent prompt injection (#248)#342Shraman123 wants to merge 1 commit into
Shraman123 wants to merge 1 commit into
Conversation
- Add sanitizeTextContent() that truncates long strings and strips known prompt injection patterns (tool tags, INST markers, system prefixes, 'ignore previous instructions' etc.) - Apply sanitization to user-controlled content fields: text, summary, title, and highlights in sanitizeSearchResult() - Sanitize context field in sanitizeTopLevelResponse() - Add MAX_TEXT_LENGTH (10k chars) and MAX_HIGHLIGHT_LENGTH (2k chars) caps to bound payload size Closes exa-labs#248
|
@Shraman123 is attempting to deploy a commit to the Exa Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this fixes
Issue #248 identified that text content returned from web pages
(title, text, summary, highlights, context) was not sanitized before
being passed to the AI context window.
A malicious webpage could embed strings like
<tool_call>orignore previous instructionsin its content and have them executedby the AI as instructions.
Changes
sanitizeTextContent()with truncation + injection pattern removaltext,summary,title,highlights,contextMAX_TEXT_LENGTH(10,000 chars) andMAX_HIGHLIGHT_LENGTH(2,000 chars) to bound response size
Testing
Existing TypeScript build passes. The sanitizer is pure functions
with no external dependencies — easy to unit test.
Closes #248