Files
CASAN/AINative_OKR_CASAN5/packages/casan-harness/scripts/bash/artifact-scan.sh
T
thanhnvandClaude Opus 4.8 664bd1f00c feat(plan-01): Phase 1 — relocate harness code to packages/casan-harness (symlink facade)
Physically move the pure-code subtrees out of .specify into the package, leaving
compat symlinks at the old .specify/<dir> paths so every existing reference (internal
CASAN_HARNESS_ROOT + external CI/docker/mjs) keeps resolving. Runtime state stays put.

Moved (git mv): scripts/ tests/ security/ templates/ config/ governance/ memory/
  .specify/<dir>  ->  packages/casan-harness/<dir>   (+ .specify/<dir> symlink)
Stays in .specify (state/governance/domain, handled later): logs/ agentops/ level5/
  init-options.json traceability-map.json

Python `.resolve()` self-location followed the compat symlink into packages and lost
the app root; generate-casan-demo-context.py, generate-agentops-dashboard.py and
dashboard-server.py now walk UP for the `.specify` state marker instead of a fixed
parent depth (fixes "missing trace files" in run-casan4).

Full gate: PASS=64 FAIL=0 SKIP=3 (CASAN_CI_STEP_TIMEOUT_SEC=1200 — track-a ~450s runs
close to the 600s default and can tip over under load; this is timing variance, not a
regression — it passed cleanly with headroom). Runtime log/audit artifacts kept unstaged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 00:06:00 +09:00

50 lines
1.7 KiB
Bash
Executable File

#!/usr/bin/env bash
set -uo pipefail
# CASAN WP-S7 — Artifact indirect injection scanner.
# Before a sub-agent reads an artifact (spec, plan, context YAML, etc.),
# this script scans its content for prompt-injection patterns.
# Untrusted content sourced from external systems or user-supplied inputs
# could carry injections that target downstream model calls.
#
# Usage:
# artifact-scan.sh <artifact-file> [context-label]
#
# Exit:
# 0 — artifact is safe to use
# 2 — injection pattern detected in artifact (pipeline should reject/quarantine)
# 64 — usage error (file missing)
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ARTIFACT="${1:-}"
LABEL="${2:-unknown-artifact}"
if [[ -z "$ARTIFACT" || ! -f "$ARTIFACT" ]]; then
echo "Usage: artifact-scan.sh <artifact-file> [context-label]" >&2
exit 64
fi
WORK="$(mktemp -d)"; trap 'rm -rf "$WORK"' EXIT
SCAN_OUT="$WORK/artifact-scan-out.txt"
# Run security-check.sh in 'input' mode on the artifact — this covers
# blocklist + normalization + semantic (if CASAN_SEMANTIC_CLASSIFY=1).
# We force semantic OFF here so the scan is fast; the caller can enable
# it for high-risk artifacts.
CASAN_SEMANTIC_CLASSIFY="${CASAN_SEMANTIC_CLASSIFY:-0}" \
bash "$SCRIPT_DIR/security-check.sh" "$ARTIFACT" "$SCAN_OUT" input 2>/dev/null
SC_RC=$?
TIMESTAMP="$(date -u +"%Y-%m-%dT%H:%M:%SZ")"
if [[ "$SC_RC" -eq 2 ]]; then
echo "ARTIFACT_SCAN_BLOCKED label=$LABEL file=$ARTIFACT reason=injection_detected timestamp=$TIMESTAMP"
exit 2
elif [[ "$SC_RC" -ne 0 ]]; then
echo "ARTIFACT_SCAN_ERROR label=$LABEL rc=$SC_RC" >&2
exit 2 # fail closed on scan error
else
echo "ARTIFACT_SCAN_CLEAN label=$LABEL file=$ARTIFACT timestamp=$TIMESTAMP"
exit 0
fi