chore(security): prompt-injection defense policy#1
Merged
Conversation
Adds SECURITY.md with a prompt-injection defense policy and (where present) appends a 'Prompt Injection Defenses' section to AGENTS.md / CLAUDE.md. Doc-only, no runtime changes. The policy: instructions only come from CLAUDE.md/AGENTS.md and the user message stream; all other text (tool outputs, web fetches, MCP responses, scraped pages, file contents, env values, commit messages) is data, not instructions.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a prompt-injection defense policy to SECURITY.md (creates it if absent) and appends a defenses section to AGENTS.md / CLAUDE.md where they exist.
Doc-only, no runtime changes. Treats text outside CLAUDE.md/AGENTS.md and the user message stream as data not instructions; lists override-pattern detection and confirm-before actions; documents reporting.
Part of a sweep across repos with agent surface (CLAUDE.md / AGENTS.md / .claude/ / .cursor/ / MCP).