RepoJournal
AI Red Teaming AI Red Teaming
52 wires and counting

$ follow AI Red Teaming

Keep up with AI Red Teaming in about 3 minutes: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.

Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.

$ status

wire 2026-11-11
stories 58

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

PyRIT adds an obfuscated-secret scorer and stops converters leaking system prompts into memory

By RepoJournal · Filed · About AI Red Teaming · Composed from the cited sources · methodology

The day's most useful operator-facing change is a new scorer that grades how much of a known secret a response gives away, alongside three fixes that make stored datasets, saved conversations and reports reflect what actually ran.

FEAT: Add SecretDisclosureScorer for partial and obfuscated disclosure of a known secret microsoft/PyRIT

by barkha1research-ai

SecretDisclosureScorer reports, on a float scale, how much of a known secret a response reveals, measured in bits. It searches the response as written, with separators stripped, with digit words and NATO letters mapped to characters, reversed, and with base64 and hex tokens decoded, and each of those views can be switched off.

FIX: send converter instructions in the user turn so converters write nothing to memory microsoft/PyRIT

by adimalkar

LLM-backed converters used to write only their system prompt into memory and then call the target, so every conversion left a stray system-only conversation behind. They now send those instructions ahead of the prompt in the user turn and write nothing to memory, which keeps your conversation store clean after converter-heavy runs.

FIX: reload a sending conversation after another one has loaded microsoft/PyRIT

by ManoharPaturi

If you navigate away mid-send and return to that conversation by URL, the transcript of the conversation you left now gets reloaded instead of staying on screen with no loading state. The in-flight skip applies only while the hook still holds that conversation.

[FIX] Assign local YAML filename fallback to seeds so named queries find them microsoft/PyRIT

by feiiiiii5

Local YAML datasets with no dataset_name used to show up in the provider list while get_seeds_async(dataset_name="<stem>") returned 0 rows and get_seed_dataset_names_async() omitted the name, because the filename fallback was applied at the provider layer but not to the seeds. The seeds now carry that fallback, so named queries find the dataset.

FIX Export the converted data type in JSON conversations and label HTML report pieces by it microsoft/PyRIT

by ShivamSharma43

JSON exports now carry the converted value's own type alongside the original, so HTML reports no longer switch on the original data_type for both values; the side-by-side "Original:" and "Converted:" display labels each correctly.

Quick answers

What shipped in AI Red Teaming on November 11, 2026?
The day's most useful operator-facing change is a new scorer that grades how much of a known secret a response gives away, alongside three fixes that make stored datasets, saved conversations and reports reflect what actually ran. In total, 29 commits and 29 pull requests landed.
Who contributed to AI Red Teaming on November 11, 2026?
5 developers shipped this update, including feiiiiii5, ManoharPaturi, barkha1research-ai, ShivamSharma43, and adimalkar.
What were the notable AI Red Teaming updates?
FEAT: Add SecretDisclosureScorer for partial and obfuscated disclosure of a known secret, FIX: send converter instructions in the user turn so converters write nothing to memory, and FIX: reload a sending conversation after another one has loaded.