packages/mosaic/framework/tools/git/test-wrapper-guard.sh

@@ -67,6 +67,13 @@ FIXTURES="$TMP/fixtures.tsv"
   printf '0\t{"tool_input":{"command":"python3 -c '"'"'print(\\"curl -d https://git.example.invalid/api/v1/repos/a/b/issues\\")'"'"'"}}\tprinting an example is not calling it\n'
   # Command position must still catch the real thing behind operators and env.
   printf '2\t{"tool_input":{"command":"cd /tmp && GITEA_TOKEN=$T curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\ta real call behind && and an assignment is still a call\n'
+  # --- and the case the AUTHOR hit, one level in from the reported one: an
+  # operator INSIDE a quoted string is not an operator. This blocked a message
+  # that merely quoted the fixture above. Position is judged on the skeleton.
+  printf '0\t{"tool_input":{"command":"send.sh -m \\"repro was: cd /tmp && curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tan operator inside a quoted string is not an operator\n'
+  printf '0\t{"tool_input":{"command":"cat >> notes.md <<EOF\\nwe ran: curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues\\nEOF"}}\ta heredoc body is data, not code\n'
+  # ...but quotes stop being data the moment something executes them.
+  printf '2\t{"tool_input":{"command":"bash -c \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tbash -c makes the quoted text code again\n'
 } > "$FIXTURES"
 
 fail=0 n=0

packages/mosaic/framework/tools/git/wrapper-guard.sh

@@ -85,23 +85,46 @@ fi
 # and the host-anchored literal never appears, so the check read clean while the
 # write went through. The endpoint fragments below survive it, because the
 # fragment has to appear somewhere for the URL to be constructible at all.
-# The client must be at COMMAND POSITION — start of the command, or directly
-# after a shell operator, optionally behind VAR=value assignments. Substring
-# presence is not enough, and this is the second thing review caught: with a
-# bare substring test,
+# The client must be at COMMAND POSITION, and that has to be judged against the
+# CODE in the command, not against its text. Review caught the text version
+# blocking ordinary work:
 #   grep -R "curl -d https://host/api/v1/repos/a/b/issues" docs/
 #   echo "curl -d https://host/api/v1/repos/a/b/pulls" > note.txt
-# were both BLOCKED. Talking about a call is not making one. Over-blocking is
-# not the safe direction here — a guard that blocks ordinary work gets switched
-# off, and a guard that is off permits everything.
+# Talking about a call is not making one, and over-blocking is not the safe
+# direction: a guard that blocks ordinary work gets switched off, and a guard
+# that is off permits everything.
 #
-# Quoting is what separates the two: in every false positive the client sits
-# immediately after a quote character, never after an operator. Note the
-# deliberate absence of quote-stripping: the URL is frequently quoted in REAL
-# calls, so stripping quotes before matching would blind the endpoint check.
+# A first fix required the client to follow a shell operator. That lasted until
+# the author sent a message quoting one of these fixtures — the quoted text
+# contained `... && GITEA_TOKEN=$T curl -d@b .../merge`, so an operator appeared
+# INSIDE the quotes and the guard blocked the message. Same defect, one level
+# in: an operator inside a string is not an operator.
+#
+# So the position test runs against a SKELETON — the command with its data spans
+# (quoted strings, heredoc bodies) removed. Endpoint, URL and body detection all
+# still run against the FULL text, because real calls quote their URLs and a
+# skeleton would be blind to them.
+#
+# The exception is the reason quotes are data at all: if something is about to
+# EXECUTE the quoted text (`bash -c`, `sh <<EOF`, `eval`), then the quotes hold
+# code and the skeleton is the full text again.
+if printf '%s' "$CMD" | grep -Eq '(^|[[:space:]])((ba|z)?sh[[:space:]]+-c|(ba|z)?sh[[:space:]]*<<|eval[[:space:]])'; then
+  # Quotes become command separators rather than disappearing: in `bash -c
+  # "curl ..."` the client IS at command position, just one interpreter down.
+  SKEL="$(printf '%s' "$CMD" | tr "\"'" ';;')"
+else
+  # Heredoc bodies first (line-oriented), then quoted spans (span-oriented).
+  SKEL="$(printf '%s' "$CMD" | awk '
+    { if (hd != "") { if ($0 == hd) hd=""; next }
+      if (match($0, /<<-?[[:space:]]*'"'"'?"?[A-Za-z_][A-Za-z0-9_]*/)) {
+        t = substr($0, RSTART, RLENGTH); sub(/^<<-?[[:space:]]*['"'"'"]?/, "", t); hd = t
+      }
+      print }' | sed "s/'[^']*'//g; s/\"[^\"]*\"//g")"
+fi
+
 CLIENT_AT_CMD_POS='(^|[;&|(){}]|`|\$\()[[:space:]]*([A-Za-z_][A-Za-z0-9_]*=[^[:space:]]*[[:space:]]+)*(curl|wget|httpie|http)([[:space:]]|$)'
 
-if printf '%s' "$CMD" | grep -Eq "$CLIENT_AT_CMD_POS" \
+if printf '%s' "$SKEL" | grep -Eq "$CLIENT_AT_CMD_POS" \
    && printf '%s' "$CMD" | grep -Eq 'https?://'; then
 
   # Write detection. Every spelling curl accepts, because the guard is defeated