 thanhnvandClaude Opus 4.8
|
ac40c0b281
|
feat(h4-hardening): Plan-07 Track A — A1 strict semantic, A2 unicode/encoding, A3 tool-output scan
A1 (V1): CASAN_SECURITY_STRICT=1 makes semantic classification REQUIRED and
fail-closed — model unavailable/no-verdict → BLOCK, never a silent SKIP.
Non-strict CASAN_SEMANTIC_CLASSIFY=1 keeps regex verdict but logs
SEMANTIC_SKIPPED loudly (sourced casan-log.sh). Default (no flags) unchanged.
A2 (V3/V4): unicode-normalize.py (NFKC + zero-width strip + Cyrillic/Greek
homoglyph fold) and decode-suspicious.py (base64/hex decode + rescan, printable
filter to avoid false positives) feed new match_either/secret_match haystacks.
Blocks homoglyph, zero-width, fullwidth, base64/hex-smuggled injection & secrets.
A3 (V7): tool-output-scan.sh scans tool output for injection/secret before it
re-enters model context; wrapper runs it after H6-exec (mode off|warn|block,
strict→block). warn is default to preserve benign-draft behaviour.
Baseline preserved: run-casan4 35/35, adversarial 44/44.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-03 22:20:50 +09:00 |
|
|
Nam Pham Dinh ThanhandClaude Sonnet 4.6
|
838b2473b6
|
Wave 4: frontend Vitest tests, H1/H7 fixes, Windows compat (python3→python, MSYS2 path)
WV4-A: Added 16 Vitest/RTL tests to frontend (jsdom env, fail-before proof verified)
WV4-B: Created 12 stub traces for pipeline retention gap; fixed MSYS2/Python path mismatch in context-validate.sh; run-casan4-harness-tests.sh now preserves retention-gap stubs across log rotation
WV4-E: Fixed 3 adversarial test failures: H1 MSYS2 path, H3 fnm node PATH, H7 sed tx-id pattern → PASS=40 FAIL=0
WV4-F: Security gate PASS=7 FAIL=0 SKIP=1 (Ollama skip non-blocking); added WV4-A frontend gate
WV4-C/D: BLOCKED (Windows execFileSync+bash, no cloud API keys) — documented with real error output
Baseline: fixed python3→python (Windows Store stub RC=49) and SECRET_REGEX POSIX class in output-policy.yaml
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-07-01 02:23:51 +09:00 |
|