You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Prompt InjectionArea: what it touches
ImprovementsKind: in v2.1.232,
ImprovementsSection of the release
What
The filter that neutralizes instruction-shaped text coming back from a subagent was rebuilt to see through disguises: homoglyph letters, alternate dash and colon characters, and invisible formatting characters inserted between letters no longer get a fake tag past it. It runs on every subagent result with no flag around it.
Details
Covers the same five rules as before: system reminder tags, harness envelope tags, channel source tags, marker prefix forgery, and model layer tags. Previously each was a hand-written ASCII regex plus literal constants for antml: and <channel source=".
The neutralizer now appends a backslash to whatever matched, rather than rewriting a literal <.
A guard in the pattern builder rejects tag names outside lowercase [a-z0-9_-].
The warning banner shown to you is unchanged and still describes the substitution as < becoming <\.
Evidence
confusableTagScrubPattern: tag names are lowercase [a-z0-9_-]
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
