diff --git a/sanitize.config.json b/sanitize.config.json index 580af1b..63c9c4a 100644 --- a/sanitize.config.json +++ b/sanitize.config.json @@ -21,7 +21,8 @@ "a specific dataset accession ID, file path, or repository tied to one private/in-progress study (e.g. an embargoed OpenNeuro dataset)", "names of collaborators, PIs, reviewers, or institutions tied to one active engagement (not public co-author lists)", "grant numbers, IRB/ethics protocol numbers, or funding details specific to one engagement", - "a codename or label that identifies one particular study (e.g. used as a skill name or heading)" + "a codename or label that identifies one particular study (e.g. used as a skill name or heading)", + "a messaging or account identifier tied to a real person — a Signal/Telegram UUID, a contact phone, an allowlisted user ID (these belong in deployment config/secrets, never in the package)" ], "do_not_flag_examples": [ "generic methodology (\"how to verify a citation\", \"how to grade a source\")", diff --git a/scripts/check_sanitization.py b/scripts/check_sanitization.py index 55213fc..ab33baa 100644 --- a/scripts/check_sanitization.py +++ b/scripts/check_sanitization.py @@ -59,6 +59,9 @@ def load_config(root="."): ("private-key-block", re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH |DSA |PGP )?PRIVATE KEY-----")), ("email", re.compile(r"\b[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}\b")), ("us-phone", re.compile(r"(?