thanhnvandClaude Opus 4.8
664bd1f00c
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>
53 lines
2.0 KiB
Bash
Executable File
53 lines
2.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -uo pipefail
|
|
|
|
# CASAN H4 — Tool-output indirect-injection scanner (Track A, V7).
|
|
#
|
|
# A tool (shell command, file read, web fetch, sub-agent) can return content
|
|
# that is then fed back into a downstream model's context. If that content
|
|
# carries a prompt injection, the model can be hijacked even though the ORIGINAL
|
|
# user input was clean. This scans a tool-output file the same way an untrusted
|
|
# artifact is scanned, BEFORE the output is allowed to re-enter model context.
|
|
#
|
|
# It reuses security-check.sh in `input` mode (block-pattern + unicode/encoding
|
|
# normalization + secret detection) but forces the semantic/strict model path
|
|
# OFF so the scan is deterministic and needs no model backend — this is a
|
|
# pattern scan of machine output, not a user-intent classification.
|
|
#
|
|
# Usage:
|
|
# tool-output-scan.sh <tool-output-file> [context-label]
|
|
# Exit:
|
|
# 0 — safe to reuse
|
|
# 2 — injection / secret pattern detected (caller should reject/quarantine)
|
|
# 64 — usage error (file missing)
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
OUTPUT_FILE="${1:-}"
|
|
LABEL="${2:-unknown-tool}"
|
|
|
|
if [[ -z "$OUTPUT_FILE" || ! -f "$OUTPUT_FILE" ]]; then
|
|
echo "Usage: tool-output-scan.sh <tool-output-file> [context-label]" >&2
|
|
exit 64
|
|
fi
|
|
|
|
WORK="$(mktemp -d)"; trap 'rm -rf "$WORK"' EXIT
|
|
SCAN_OUT="$WORK/tool-output-scan.txt"
|
|
TIMESTAMP="$(date -u +"%Y-%m-%dT%H:%M:%SZ")"
|
|
|
|
# Deterministic pattern scan: semantic + strict explicitly disabled here so a
|
|
# tool-output scan never depends on (or is blocked by) model availability.
|
|
CASAN_SECURITY_STRICT=0 CASAN_SEMANTIC_CLASSIFY=0 \
|
|
bash "$SCRIPT_DIR/security-check.sh" "$OUTPUT_FILE" "$SCAN_OUT" input >/dev/null 2>&1
|
|
SC_RC=$?
|
|
|
|
if [[ "$SC_RC" -eq 2 ]]; then
|
|
echo "TOOL_OUTPUT_SCAN_BLOCKED label=$LABEL file=$OUTPUT_FILE reason=injection_or_secret timestamp=$TIMESTAMP"
|
|
exit 2
|
|
elif [[ "$SC_RC" -ne 0 ]]; then
|
|
echo "TOOL_OUTPUT_SCAN_ERROR label=$LABEL rc=$SC_RC" >&2
|
|
exit 2 # fail closed on scan error
|
|
fi
|
|
|
|
echo "TOOL_OUTPUT_SCAN_CLEAN label=$LABEL file=$OUTPUT_FILE timestamp=$TIMESTAMP"
|
|
exit 0
|