Repository navigation
docs: list the prompt-injection layers and the setup budget as built - #349
Merged
Merged
Conversation
"Stay private and safe" now covers flagging instruction-like text (patterns or the optional local classifier, #329, #347), asking before the browser acts on what the assistant wrote (#333), breaking up links in chat-room answers (#338), the archive as data over MCP (#343) and the audit log of what was caught (#344). "See what it costs" adds the overall budget asked for in setup (#281). "In progress" drops what merged and adds #337, #341 and #346. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HDx7PPUauyjMn1LZs8JAsS
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Adeel · project thread
Description
Before: the README listed flagging instruction-like text (#329), asking before the browser acts on what the assistant wrote (#333) and the budget in setup (#281) under "In progress", though they merged, and didn't mention #338, #343, #344 or #347.
After: "Stay private and safe" describes the prompt-injection layers: text marked as data, instruction-like text flagged by free patterns or an optional local classifier fetched only when picked (#329, #347), sending out or the browser acting waits for a yes (#309, #333), chat-room answers have self-built links broken up (#338), agents get the archive as data over MCP (#343), and what was caught goes into the audit log (#344). "See what it costs" adds the overall budget with soft and hard limits that setup asks for after a cloud model (#281). "In progress" drops what merged and adds #337, #341 and #346.
Motivation and Context
Keeps the README honest as PRs merge, per Adeel's ask to update the README and feature list.
Types of changes
Documentation only.
Checklist:
mkdocs build --strictclean locally.Done questions (AGENTS.md)
🤖 Generated with Claude Code
https://claude.ai/code/session_01HDx7PPUauyjMn1LZs8JAsS
Generated by Claude Code