Create body_prompt_injection_llm_instructions_new_sender.yml - #5259
Draft
sublimebrian wants to merge 6 commits into
Draft
Create body_prompt_injection_llm_instructions_new_sender.yml#5259sublimebrian wants to merge 6 commits into
sublimebrian wants to merge 6 commits into
Conversation
sublimebrian
added
the
in-test-rules
github-actions Bot
added a commit
that referenced
this pull request
Sep 4, 2026
…ns directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 4, 2026
…Body instructions directed at an LLM from a new sender
Replace the unconditional graymail exclusion and the TEMPORARY hardcoded sender list with a single condition that excludes graymail only when the sender passes DMARC. Authenticated bulk senders are still suppressed without maintaining a domain list, and unauthenticated senders whose payload scores graymail no longer bypass the rule.
github-actions Bot
added a commit
that referenced
this pull request
Sep 4, 2026
…tions directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 4, 2026
…n: Body instructions directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 8, 2026
…tions directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 8, 2026
…n: Body instructions directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 9, 2026
…n: Body instructions directed at an LLM from a new sender
github-actions Bot
added a commit
that referenced
this pull request
Sep 9, 2026
…tions directed at an LLM from a new sender
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
2 participants
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.
Summary
New detection rule: Prompt injection: Body instructions directed at an LLM from a new sender.
Flags inbound messages whose plaintext body contains instructions aimed at an LLM (
beta.prompt_injection_detection) when the sender has no established, benign relationship (profile.by_sender()prevalence of new/outlier/rare and no prior benign messages). Graymail is excluded viabeta.fuzzy_attack_score(), and a temporary allowlist suppresses DMARC-authenticated mail from a set of high-volume legitimate newsletter/service domains.Notes
// TEMPORARYDMARC allowlist is a stopgap to suppress known-benign newsletter senders while the PI signal is tuned; expected to be removed once the model's false-positive rate on these senders drops.