fix: address Copilot PR review comments on governance-audit hook

- Switch from colon to tab delimiter to handle colons in evidence text
- Base64-encode evidence to prevent parsing issues
- Use MAX_SEVERITY in log output and JSON events
- Narrow regex patterns to reduce false positives:
  - third[_-]?party instead of third.?party
  - Role reassignment scoped to AI terms
  - System prompt injection requires 'you are' context
- Fix session-end stats to scope to current session only
- Update privacy statement to clarify evidence snippets are logged
- Rename credential description to 'Possible hardcoded credential'
- Fix database destruction regex to also match semicolons

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Imran Siddique
2026-02-18 14:49:17 -08:00
parent 4a4b9343d5
commit 32d8f7f622
3 changed files with 28 additions and 14 deletions

View File

@@ -93,7 +93,7 @@ Events are written to `logs/copilot/governance/audit.log` in JSON Lines format:
## Privacy & Security
- Prompts are **never** logged — only threat signals and metadata are recorded
- Full prompts are **never** logged — only matched threat patterns (minimal evidence snippets) and metadata are recorded
- Add `logs/` to `.gitignore` to keep audit data local
- Set `SKIP_GOVERNANCE_AUDIT=true` to disable entirely
- All data stays local — no external network calls

View File

@@ -44,13 +44,15 @@ check_pattern() {
if echo "$PROMPT" | grep -qiE "$pattern"; then
local evidence
evidence=$(echo "$PROMPT" | grep -oiE "$pattern" | head -1)
THREATS_FOUND+=("$category:$severity:$description:$evidence")
local evidence_encoded
evidence_encoded=$(printf '%s' "$evidence" | base64 | tr -d '\n')
THREATS_FOUND+=("$category $severity $description $evidence_encoded")
fi
}
# Data exfiltration signals
check_pattern "send\s+(all|every|entire)\s+\w+\s+to\s+" "data_exfiltration" "0.8" "Bulk data transfer"
check_pattern "export\s+.*\s+to\s+(external|outside|third.?party)" "data_exfiltration" "0.9" "External export"
check_pattern "export\s+.*\s+to\s+(external|outside|third[_-]?party)" "data_exfiltration" "0.9" "External export"
check_pattern "curl\s+.*\s+-d\s+" "data_exfiltration" "0.7" "HTTP POST with data"
check_pattern "upload\s+.*\s+(credentials|secrets|keys)" "data_exfiltration" "0.95" "Credential upload"
@@ -61,16 +63,16 @@ check_pattern "add\s+.*\s+(sudoers|administrators)" "privilege_escalation" "0.95
# System destruction signals
check_pattern "(rm\s+-rf\s+/|del\s+/[sq]|format\s+c:)" "system_destruction" "0.95" "Destructive command"
check_pattern "(drop\s+database|truncate\s+table|delete\s+from\s+\w+\s*$)" "system_destruction" "0.9" "Database destruction"
check_pattern "(drop\s+database|truncate\s+table|delete\s+from\s+\w+\s*(;|\s*$))" "system_destruction" "0.9" "Database destruction"
check_pattern "wipe\s+(all|entire|every)" "system_destruction" "0.9" "Mass deletion"
# Prompt injection signals
check_pattern "ignore\s+(previous|above|all)\s+(instructions?|rules?|prompts?)" "prompt_injection" "0.9" "Instruction override"
check_pattern "you\s+are\s+now\s+(a|an)\s+" "prompt_injection" "0.7" "Role reassignment"
check_pattern "system\s*:\s*" "prompt_injection" "0.6" "System prompt injection"
check_pattern "you\s+are\s+now\s+(a|an)\s+(assistant|ai|bot|system|expert|language\s+model)\b" "prompt_injection" "0.7" "Role reassignment"
check_pattern "(^|\n)\s*system\s*:\s*you\s+are" "prompt_injection" "0.6" "System prompt injection"
# Credential exposure signals
check_pattern "(api[_-]?key|secret[_-]?key|password|token)\s*[:=]\s*['\"]?\w{8,}" "credential_exposure" "0.9" "Hardcoded credential"
check_pattern "(api[_-]?key|secret[_-]?key|password|token)\s*[:=]\s*['\"]?\w{8,}" "credential_exposure" "0.9" "Possible hardcoded credential"
check_pattern "(aws_access_key|AKIA[0-9A-Z]{16})" "credential_exposure" "0.95" "AWS key exposure"
# Log the prompt event
@@ -80,7 +82,9 @@ if [[ ${#THREATS_FOUND[@]} -gt 0 ]]; then
FIRST=true
MAX_SEVERITY="0.0"
for threat in "${THREATS_FOUND[@]}"; do
IFS=':' read -r category severity description evidence <<< "$threat"
IFS=$'\t' read -r category severity description evidence_encoded <<< "$threat"
local evidence
evidence=$(printf '%s' "$evidence_encoded" | base64 -d 2>/dev/null || echo "[redacted]")
if [[ "$FIRST" != "true" ]]; then
THREATS_JSON+=","
@@ -104,14 +108,15 @@ if [[ ${#THREATS_FOUND[@]} -gt 0 ]]; then
jq -Rn \
--arg timestamp "$TIMESTAMP" \
--arg level "$LEVEL" \
--arg max_severity "$MAX_SEVERITY" \
--argjson threats "$THREATS_JSON" \
--argjson count "${#THREATS_FOUND[@]}" \
'{"timestamp":$timestamp,"event":"threat_detected","governance_level":$level,"threat_count":$count,"threats":$threats}' \
'{"timestamp":$timestamp,"event":"threat_detected","governance_level":$level,"threat_count":$count,"max_severity":($max_severity|tonumber),"threats":$threats}' \
>> "$LOG_FILE"
echo "⚠️ Governance: ${#THREATS_FOUND[@]} threat signal(s) detected"
echo "⚠️ Governance: ${#THREATS_FOUND[@]} threat signal(s) detected (max severity: $MAX_SEVERITY)"
for threat in "${THREATS_FOUND[@]}"; do
IFS=':' read -r category severity description evidence <<< "$threat"
IFS=$'\t' read -r category severity description _evidence_encoded <<< "$threat"
echo " 🔴 [$category] $description (severity: $severity)"
done

View File

@@ -15,12 +15,21 @@ mkdir -p logs/copilot/governance
TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
LOG_FILE="logs/copilot/governance/audit.log"
# Count events from this session
# Count events from this session (filter by session start timestamp)
TOTAL=0
THREATS=0
SESSION_START=""
if [[ -f "$LOG_FILE" ]]; then
# Find the last session_start event to scope stats to current session
SESSION_START=$(grep '"session_start"' "$LOG_FILE" 2>/dev/null | tail -1 | jq -r '.timestamp' 2>/dev/null || echo "")
if [[ -n "$SESSION_START" ]]; then
# Count events after session start
TOTAL=$(awk -v start="$SESSION_START" -F'"timestamp":"' '{split($2,a,"\""); if(a[1]>=start) count++} END{print count+0}' "$LOG_FILE" 2>/dev/null || echo 0)
THREATS=$(awk -v start="$SESSION_START" -F'"timestamp":"' '{split($2,a,"\""); if(a[1]>=start && /threat_detected/) count++} END{print count+0}' "$LOG_FILE" 2>/dev/null || echo 0)
else
TOTAL=$(wc -l < "$LOG_FILE" 2>/dev/null || echo 0)
THREATS=$(grep -c '"threat_detected"' "$LOG_FILE" 2>/dev/null || echo 0)
fi
fi
jq -Rn \