7bd77d6268778ece04edbddb1dff268a738ffced
2 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Tom Boucher
|
7bd77d6268 |
fix(116): locale-safe base64-scan with portable timeout and partial-scan signaling (#132)
* test(116): reproduce base64-scan illegal byte sequence on non-UTF8 fixtures Adds regression fixtures and failing tests for #116. Empirically verified on macOS 26.5 (BSD tr) that `tr -cd '[:print:]'` under LC_CTYPE=en_US.UTF-8 exits non-zero with "Illegal byte sequence" when its input contains bytes that are not valid UTF-8 start sequences (e.g. lone continuation bytes 0x80–0x9F). The base64-scan.sh root cause is a known bash pitfall: the assignment `local printable_count=$(... | tr -cd '[:print:]' | ...)` uses `local` on the same line, which always returns exit 0, masking the tr failure. Result: tr errors surface only on stderr; the scan exits 0 with incomplete coverage (false-clean signal). Two new tests FAIL on origin/main: - "scans non-UTF8 file containing a b64 blob without emitting Illegal byte sequence" - "dir scan with non-UTF8 files under non-C locale completes cleanly within 30s" Fixtures in tests/fixtures/base64-locale/: utf8-with-injection.md — UTF-8 + base64-encoded injection (positive control) non-utf8-with-b64blob.bin — raw 0x80-0x9F bytes + b64 blob that decodes to binary (this is the reproducer that triggers tr error) mixed-encoding.txt — valid UTF-8 + lone continuation bytes clean-text.md — negative control (must not be flagged) Test helpers use spawnSync (not execFileSync) so stderr is captured even on exit 0 — execFileSync only surfaces stderr via the thrown error on non-zero exit. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(116): locale-safe base64-scan with portable timeout and partial-scan signaling Root cause: BSD tr(1) on macOS rejects input bytes that are not valid UTF-8 start sequences with "Illegal byte sequence" when LC_CTYPE is set to any UTF-8 locale (e.g. en_US.UTF-8). Empirically verified on macOS 26.5 using `man tr` (ENVIRONMENT section) and direct testing: printf '\x80\x81hello' | LC_ALL=en_US.UTF-8 tr -cd '[:print:]' → tr: Illegal byte sequence (exit 1) The error is silently masked because base64-scan.sh uses `local` on the same line as the tr assignment. Bash's `local` built-in always returns 0 regardless of the subshell's exit code — so the tr failure never propagates under `set -euo pipefail`. Result: the script exits 0 with truncated printable_count, causing binary-decoded blobs to be skipped (false-clean, security gap). Fix: `export LC_ALL=C` at script level (line 33). - LC_ALL=C forces the POSIX C locale throughout: tr treats every byte 0x00–0xFF as a valid character, never rejects high bytes. - Safe for all script operations: all injection patterns are ASCII, grep POSIX classes ([:space:], [:print:]) behave correctly in C locale, base64 -d is locale-independent. - Script-level export is appropriate because all operations in this script are byte-level; no multi-byte character handling is needed. Additional hardening: - MAX_LINE_BYTES=1048576 guard in extract_and_check_blobs: lines longer than 1 MiB are skipped with an explicit "partial scan" warning to stderr. This bounds grep -oE cost on pathological inputs (minified JS, single-line binary blobs) and satisfies the "partial-scan failure signaling" requirement. - Portable run_with_timeout + is_timeout_exit: probes for GNU timeout, gtimeout (homebrew), and falls back to perl alarm(N)+exec. Defined for future use guarding external sub-commands. Verified: no timeout binary on this macOS host, perl alarm fallback works correctly (exit 142 on SIGALRM). Test-rigor fixes applied per test-rigor skill review: - Fixture validity check: assert `isInvalidUtf8` (round-trip length difference) rather than checking for a specific byte range — the property that matters is "file is not valid UTF-8", not "file has bytes in 0x80–0x9F". - FAIL assertions: assert `FAIL: ${INJECTION_FIXTURE}` (specific filepath) not `result.stdout.includes('FAIL')` — rules out false-positives on other fixtures. - Test name: renamed "mixed-encoding file does not cause scan to abort or hang" to accurately describe what is tested (no extractable blobs → exits clean). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(116): fix shellcheck warnings in base64-scan.sh Address SC2034 (unused variables) and SC2329 (functions never invoked) warnings flagged by shellcheck after the locale-hardening changes. SC2034 fixes (pre-existing): - Remove unused SCRIPT_DIR variable (set but never referenced) - Remove unused printable_ratio local (declared but no assignment or use) SC2329 fixes (new functions from this PR): - Add shellcheck disable=SC2329 annotations on run_with_timeout, _init_timeout_cmd, and is_timeout_exit — these are intentionally defined as infrastructure helpers, not called from the main loop. The line-length guard (MAX_LINE_BYTES) is the primary runtime protection; the timeout helpers are available for future use. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(#116): exclude scanner fixtures from base64-scan diff mode Add tests/fixtures/* to should_skip_file() so deliberate prompt-injection samples in scanner fixture directories are never flagged in CI diff-mode. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
feec5a37a2 |
ci(security): add prompt injection, base64, and secret scanning
Add CI security pipeline to catch prompt injection attacks, base64-obfuscated payloads, leaked secrets, and .planning/ directory commits in PRs. This is critical for get-shit-done because the entire codebase is markdown prompts — a prompt injection in a workflow file IS the attack surface. New files: - scripts/prompt-injection-scan.sh: scans for instruction override, role manipulation, system boundary injection, DAN/jailbreak, and tool call injection patterns in changed files - scripts/base64-scan.sh: extracts base64 blobs >= 40 chars, decodes them, and checks decoded content against injection patterns (skips data URIs and binary content) - scripts/secret-scan.sh: detects AWS keys, OpenAI/Anthropic keys, GitHub PATs, Stripe keys, private key headers, and generic credential patterns - .github/workflows/security-scan.yml: runs all three scans plus a .planning/ directory check on every PR - .base64scanignore / .secretscanignore: per-repo false positive allowlists - tests/security-scan.test.cjs: 51 tests covering script existence, pattern matching, false positive avoidance, and workflow structure All scripts support --diff (CI), --file, and --dir modes. Cross-platform (macOS + Linux). SHA-pinned actions. Environment variables used for github context in run blocks (no direct interpolation). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |