🛡️ Sentinel: [CRITICAL] Fix integer coercion vulnerability in readline input validation

.Rbuildignore

@@ -22,3 +22,6 @@
 ^\.jules(/.*)?$
 ^\.trivyignore\.yaml$
 ^trivy\.yaml$
+.semgrepignore
+test_dummy.R
+test_validation.R

.jules/sentinel.md

@@ -2,3 +2,8 @@
 **Vulnerability:** Unvalidated inputs passed to `if()` statements can cause process crashes (`condition has length > 1`) or unexpected coercion vulnerabilities.
 **Learning:** In R, optional boolean parameters that default to `NULL` should be validated using explicit runtime type validation (e.g., `if (!is.null(flag) && (!is.logical(flag) || length(flag) != 1 || is.na(flag)))`).
 **Prevention:** Always implement explicit runtime type validation for optional boolean parameters.
+
+## 2024-08-08 - Fix missing input validation leading to NAs
+**Vulnerability:** Weak regex `grepl("^[0-9]+$", n)` allows large numbers that coerce to `NA` via `as.integer()`, potentially causing unhandled exceptions in conditionals.
+**Learning:** Always use tightly bounded exact-match regex like `grepl("^[12]$", n)` when validating user inputs for integer choices to avoid coercion crashes and DoS vulnerabilities.
+**Prevention:** Strictly bound input validation regexes for choices.

DESCRIPTION

@@ -10,7 +10,7 @@ Description: Automates fixed item parameter linking for test linking under
     the item response theory paradigm using mirt package estimates.
 License: GPL-3 | file LICENSE
 Imports: mirt, methods
-Suggests: testthat (>= 3.0.0)
+Suggests: testthat (>= 3.0.0), mockery
 Encoding: UTF-8
 Config/testthat/edition: 3
 Config/roxygen2/version: 8.0.0

R/aFIPC.R

@@ -141,7 +141,7 @@ autoFIPC <-
       }
       for (attempt in seq_len(3)) {
         n <- readline(prompt = "Is it correct? (1: Yes 2: No) : ")
-        if (grepl("^[0-9]+$", n)) {
+        if (grepl("^[12]$", n)) {
           return(as.integer(n))
         }
       }
@@ -171,7 +171,7 @@ autoFIPC <-
               readline(
                 prompt = "Do you want to use default BILOG-MG priors for oldform Data? (1: Yes 2: No) : "
               )
-            if (grepl("^[0-9]+$", n)) {
+            if (grepl("^[12]$", n)) {
               return(as.integer(n))
             }
           }
@@ -390,7 +390,7 @@ autoFIPC <-
               readline(
                 prompt = "Do you want to use default BILOG-MG priors for newform Data? (1: Yes 2: No) : "
               )
-            if (grepl("^[0-9]+$", n)) {
+            if (grepl("^[12]$", n)) {
               return(as.integer(n))
             }
           }

tests/testthat/test-sentinel-validation.R

@@ -35,3 +35,24 @@ test_that("autoFIPC validates boolean flags for newformBILOGprior, oldformBILOGp
     "Security Error: confirmCommonItems must be a single non-NA logical value or NULL"
   )
 })
+
+test_that("autoFIPC validates invalid readline inputs safely", {
+  # We test the confirmCommonItems prompt
+  # If we feed "9999999999" 3 times, it should throw "Too many invalid common item confirmation attempts"
+  my_readline <- function(prompt) {
+    "9999999999"
+  }
+
+  mockery::stub(aFIPC::autoFIPC, 'interactive', TRUE)
+  mockery::stub(aFIPC::autoFIPC, 'readline', my_readline)
+
+  expect_error(
+    aFIPC::autoFIPC(
+      newformXData = data.frame(A=1),
+      oldformYData = data.frame(A=2),
+      newformCommonItemNames = c('A'),
+      oldformCommonItemNames = c('A')
+    ),
+    "Too many invalid common item confirmation attempts"
+  )
+})