config: support Ubuntu — replace grep -P with grep -E, add distro-agnostic guideline

Author: benvinegar

AGENTS.md

@@ -110,6 +110,7 @@ Add new test files to `bin/test.sh` — don't scatter test invocations across CI
 - Skills are deployed from `pi/skills/` → agent's `~/.pi/agent/skills/`.
 - Agent commits operational learnings to its own skills dir (not back to source).
 - **When changing behavior, update all docs.** Check and update: `README.md`, `CONFIGURATION.md`, skill files (`pi/skills/*/SKILL.md`), and `AGENTS.md`. Inline code examples in docs must match the actual implementation.
+- **No distro-specific commands.** Scripts must work on both Arch and Ubuntu (and any standard Linux). Use `grep -E` (not `grep -P`), POSIX-compatible tools, and avoid package manager calls (`pacman`, `apt`, etc.). If a package is needed, document it as a prerequisite rather than auto-installing it.
 
 ## Security Notes
 

bin/hornet-safe-bash

@@ -5,6 +5,9 @@
 #
 # This is defense-in-depth — the agent's instructions also prohibit these,
 # but a successful injection might override soft instructions.
+#
+# NOTE: Avoid grep -P (Perl regex) — not available on all distros.
+# Use grep -E (extended regex) or awk instead.
 
 # Patterns that should NEVER be executed by the agent
 COMMAND="$*"
@@ -16,64 +19,67 @@ block() {
 }
 
 # Fork bomb
-if echo "$COMMAND" | grep -qP ':\(\)\s*\{.*\|.*&.*\}'; then
+if echo "$COMMAND" | grep -qE ':\(\)[[:space:]]*\{.*\|.*&.*\}'; then
   block "fork bomb"
 fi
 
 # rm -rf / or rm -rf /* (root filesystem deletion)
-if echo "$COMMAND" | grep -qP 'rm\s+(-[a-zA-Z]*f[a-zA-Z]*\s+)?(-[a-zA-Z]*r[a-zA-Z]*\s+)?(\/\s*$|\/\*|\/\s+)'; then
+if echo "$COMMAND" | grep -qE 'rm[[:space:]]+(-[a-zA-Z]*f[a-zA-Z]*[[:space:]]+)?(-[a-zA-Z]*r[a-zA-Z]*[[:space:]]+)?(/[[:space:]]*$|/\*|/[[:space:]]+)'; then
   block "recursive delete of root filesystem"
 fi
-if echo "$COMMAND" | grep -qP 'rm\s+(-[a-zA-Z]*r[a-zA-Z]*\s+)?(-[a-zA-Z]*f[a-zA-Z]*\s+)?(\/\s*$|\/\*|\/\s+)'; then
+if echo "$COMMAND" | grep -qE 'rm[[:space:]]+(-[a-zA-Z]*r[a-zA-Z]*[[:space:]]+)?(-[a-zA-Z]*f[a-zA-Z]*[[:space:]]+)?(/[[:space:]]*$|/\*|/[[:space:]]+)'; then
   block "recursive delete of root filesystem"
 fi
 
 # dd writing to block devices
-if echo "$COMMAND" | grep -qP 'dd\s+.*of=/dev/(sd|vd|nvme|xvd)'; then
+if echo "$COMMAND" | grep -qE 'dd[[:space:]]+.*of=/dev/(sd|vd|nvme|xvd)'; then
   block "dd write to block device"
 fi
 
 # mkfs on block devices
-if echo "$COMMAND" | grep -qP 'mkfs\b.*\/dev\/'; then
+if echo "$COMMAND" | grep -qE 'mkfs[^a-zA-Z].*/dev/'; then
   block "mkfs on block device"
 fi
 
 # chmod 777 on sensitive paths
-if echo "$COMMAND" | grep -qP 'chmod\s+(-[a-zA-Z]*\s+)?777\s+(\/|\/etc|\/home|\/root|\/var)'; then
+if echo "$COMMAND" | grep -qE 'chmod[[:space:]]+(-[a-zA-Z]*[[:space:]]+)?777[[:space:]]+(/|/etc|/home|/root|/var)'; then
   block "chmod 777 on sensitive path"
 fi
 
 # Curl/wget piped to shell
-if echo "$COMMAND" | grep -qP '(curl|wget)\s+.*\|\s*(ba)?sh'; then
+if echo "$COMMAND" | grep -qE '(curl|wget)[[:space:]]+.*\|[[:space:]]*(ba)?sh'; then
   block "piping download to shell"
 fi
 
 # Reverse shell patterns
-if echo "$COMMAND" | grep -qP 'bash\s+-i\s+>(&|\|)\s*/dev/tcp/'; then
+if echo "$COMMAND" | grep -qE 'bash[[:space:]]+-i[[:space:]]+>[&|][[:space:]]*/dev/tcp/'; then
   block "reverse shell (bash /dev/tcp)"
 fi
-if echo "$COMMAND" | grep -qP 'nc\s+(-[a-zA-Z]*\s+)*[0-9]+.*-e\s*(\/bin\/)?(ba)?sh'; then
+if echo "$COMMAND" | grep -qE 'nc[[:space:]]+(-[a-zA-Z]*[[:space:]]+)*[0-9]+.*-e[[:space:]]*(\/bin\/)?(ba)?sh'; then
   block "reverse shell (netcat)"
 fi
-if echo "$COMMAND" | grep -qP 'python[23]?\s+-c.*socket.*connect.*subprocess'; then
+if echo "$COMMAND" | grep -qE 'python[23]?[[:space:]]+-c.*socket.*connect.*subprocess'; then
   block "reverse shell (python)"
 fi
 
 # crontab modification (persistence)
-if echo "$COMMAND" | grep -qP '(crontab\s+-[erl]|echo.*>\s*/etc/cron)'; then
+if echo "$COMMAND" | grep -qE '(crontab[[:space:]]+-[erl]|echo.*>[[:space:]]*/etc/cron)'; then
   block "crontab modification"
 fi
 
 # Modifying /etc/passwd or /etc/shadow
-if echo "$COMMAND" | grep -qP '>\s*/etc/(passwd|shadow|sudoers)'; then
+if echo "$COMMAND" | grep -qE '>[[:space:]]*/etc/(passwd|shadow|sudoers)'; then
   block "write to system auth files"
 fi
 
 # SSH key injection to other users
-if echo "$COMMAND" | grep -qP '>\s*/home/(?!hornet_agent).*/\.ssh/authorized_keys'; then
-  block "SSH key injection to another user"
+# Can't use negative lookahead without grep -P, so match broadly then exclude our user
+if echo "$COMMAND" | grep -qE '>[[:space:]]*/home/.*/.ssh/authorized_keys'; then
+  if ! echo "$COMMAND" | grep -qE '>[[:space:]]*/home/hornet_agent/.ssh/authorized_keys'; then
+    block "SSH key injection to another user"
+  fi
 fi
-if echo "$COMMAND" | grep -qP '>\s*/root/\.ssh/authorized_keys'; then
+if echo "$COMMAND" | grep -qE '>[[:space:]]*/root/.ssh/authorized_keys'; then
   block "SSH key injection to root"
 fi
 

setup.sh

@@ -3,7 +3,7 @@
 # Run as root or with sudo from the admin user account
 #
 # Prerequisites:
-#   - Arch Linux (or similar)
+#   - Linux (tested on Arch and Ubuntu)
 #   - Docker installed
 #
 # This script:
@@ -103,7 +103,16 @@ echo "=== Configuring shared repo permissions ==="
 # Set core.sharedRepository=group on all repos so git creates objects
 # with group-write perms. Without this, umask 077 in start.sh causes
 # new .git/objects to be owner-only, breaking group access (admin user).
-for repo in "$REPO_DIR" "$HORNET_HOME/workspace/modem" "$HORNET_HOME/workspace/website"; do
+
+# Source repo — set as admin user (agent can't access admin home, and root
+# needs safe.directory due to different ownership)
+if [ -d "$REPO_DIR/.git" ]; then
+  sudo -u "$ADMIN_USER" git -C "$REPO_DIR" config core.sharedRepository group
+  echo "  ✓ $REPO_DIR"
+fi
+
+# Agent workspace repos — set as agent
+for repo in "$HORNET_HOME/workspace/modem" "$HORNET_HOME/workspace/website"; do
   if [ -d "$repo/.git" ]; then
     sudo -u hornet_agent git -C "$repo" config core.sharedRepository group
     echo "  ✓ $repo"