local-review-harness/docs/SELF_REVIEW_2026-04-30.md
Claude (review-harness setup) 70d68757f7 docs: SELF_REVIEW snapshot from f3ee472 (Phase A+B MVP)
Per PROMPT.md "Final Deliverable" — capture the harness's review of
its own repo as a tracked artifact. reports/latest/ stays gitignored
for routine runs; this snapshot is the deliverable proof.

Captured: 28 findings, 3 critical (all from tests/fixtures/insecure-repo
planted secrets, intentionally), 16 high (mostly shell-exec patterns
mentioned by name in PROMPT.md and chatd-style scripts), 6 medium,
3 low. Verdict "blocked" because of fixture criticals.

Banner header notes that fixture findings are dismissable; real
codebase secrets land in identical shape — operators dismiss the
fixture path explicitly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 01:02:19 -05:00

7.2 KiB

Scrum Test — local-review-harness-full-md

Self-review snapshot — captured 2026-04-30 against commit f3ee472 (Phase A + B MVP). Re-run with ./review-harness scrum . for live numbers.

The 3 critical findings below are from tests/fixtures/insecure-repo/ — planted on purpose to prove the secret-pattern + env-file analyzers fire. Real codebase secrets would land in the same shape; operators dismiss fixture content as known-intentional.

Generated: 2026-04-30T05:55:10.657498039Z Branch: (no git) · Commit:

Verdict

blocked — critical-severity finding present. See Confirmed Risks; rotate any leaked credentials, then re-run.

Evidence

  • repo path: /home/profit/share/local-review-harness-full-md
  • file count: 36
  • languages: Go (18), Markdown (7), TypeScript (2), YAML (2), JSON (1)
  • dependency manifests: 3 (go.mod, go.sum, tests/fixtures/clean-repo/package.json)
  • test files/dirs: 9
  • LLM review: skipped (Phase C not implemented OR provider unavailable; see model-doctor.json)

Confirmed Risks

Severity File:Line Title Evidence
high tests/fixtures/insecure-repo/.env Environment file in source tree filename=.env

Suspected Risks

Each entry is a static-scan regex hit awaiting validation (Phase D / LLM cross-check).

Severity File:Line Title Evidence
critical tests/fixtures/insecure-repo/src/handler.go:23 Possible secret committed to source const API_KEY = "sk-1234567890abcdefABCDEFGHIJKLMNOPQRSTUV"
critical tests/fixtures/insecure-repo/src/handler.go:23 Possible secret committed to source const API_KEY = "sk-1234567890abcdefABCDEFGHIJKLMNOPQRSTUV"
critical tests/fixtures/insecure-repo/src/server.js:5 Possible secret committed to source const AWS_KEY = "AKIAIOSFODNN7EXAMPLE";
high PROMPT.md:419 Shell command execution - exec(``
high PROMPT.md:420 Shell command execution - spawn(``
high PROMPT.md:421 Shell command execution - Command::new``
high PROMPT.md:423 Raw SQL interpolation - format!("SELECT``
high PROMPT.md:429 Wildcard CORS - Access-Control-Allow-Origin: *``
high internal/analyzers/checks.go:101 Shell command execution ``Command::new| + // Rust
high internal/analyzers/checks.go:140 Raw SQL interpolation rawSQLFmtRe = regexp.MustCompile((?i)(?:format!|fmt.Sprintf|String::from|f"|f')[^\n]{0,80}?(?:SELECT|INSERT|UPDA…`
high internal/analyzers/checks.go:143 Raw SQL interpolation rawSQLConcatRe = regexp.MustCompile((?i)(?:SELECT|INSERT|UPDATE|DELETE)\b[^\n]{0,40}(?:+\s*\w|%s|%v|${| + "…`
high internal/analyzers/checks.go:177 Wildcard CORS // styles: Express's res.setHeader("Access-Control-Allow-Origin", "*"),
high internal/analyzers/checks.go:180 Wildcard CORS var corsAnyRe = regexp.MustCompile(Access-Control-Allow-Origin[^\n]{0,40}*)
high internal/analyzers/checks.go:194 Wildcard CORS Reason: "Access-Control-Allow-Origin: * permits cross-origin reads from any domain. Narrow to an explicit allowlist un…
high internal/analyzers/checks.go:89 Shell command execution // === 2. shell execution (exec, spawn, Command::new, subprocess) ===
high tests/fixtures/insecure-repo/src/handler.go:14 Raw SQL interpolation q := fmt.Sprintf("SELECT * FROM users WHERE name = '%s'", name)
high tests/fixtures/insecure-repo/src/handler.go:19 Shell command execution exec.Command("bash", "-c", cmd).Run()
high tests/fixtures/insecure-repo/src/server.js:2 Wildcard CORS res.setHeader("Access-Control-Allow-Origin", "*");
medium review-harness:1-18860 Large file 18860 lines (limit: 800)
medium tests/fixtures/insecure-repo/src/handler.go:10 Hardcoded absolute path const HARDCODED_PATH = "/home/profit/secrets/key.pem"
medium tests/fixtures/insecure-repo/src/handler.go:11 Hardcoded private-network IP const SERVER_IP = "192.168.1.176"
medium tests/fixtures/insecure-repo/src/huge.go:1-901 Large file 901 lines (limit: 800)
medium tests/fixtures/insecure-repo/src/server.js:7 Mutation route in file with no visible auth app.post("/api/users", function(req, res) { /* no auth */ });
medium tests/fixtures/insecure-repo/src/server.js:8 Mutation route in file with no visible auth app.delete("/api/admin", function(req, res) { /* no auth */ });
low tests/fixtures/insecure-repo/src/handler.go:22 TODO/FIXME comment // FIXME: hardcoded creds
low tests/fixtures/insecure-repo/src/handler.go:9 TODO/FIXME comment // TODO: rotate this and move to env
low tests/fixtures/insecure-repo/src/server.js:1 TODO/FIXME comment // HACK: open CORS for now

Blocked Checks

  • LLM review (Phase 2 in REVIEW_PIPELINE.md). Reason: provider unavailable or stub. Next command: review-harness model doctor

Sprint Backlog

Sprint 0 — Reproducibility Gate

  • Wire just verify (or equivalent) to run the static checks before every commit/PR.
  • Add a CI step that fails on critical findings.
  • Triage the 28 findings emitted by this run; mark each as accepted / blocking / dismiss-with-reason.

Sprint 1 — Trust Boundary Gate

  • Resolve every critical and high finding before non-loopback deploy.
  • Confirm auth posture for any mutation endpoint flagged as exposed.
  • Replace raw SQL interpolation with parameterized queries.

Sprint 2 — Memory Correctness Gate

  • (Phase E) Wire append-only .memory/ writes for known-risks + fixed-patterns.
  • Add a regression test that re-runs the harness and asserts no regression in confirmed-finding count.

Sprint 3 — Agent Loop Reality Gate

  • (Phase C) Wire local-Ollama LLM review.
  • (Phase D) Validator pass cross-checks every LLM finding against repo evidence.

Sprint 4 — Deployment Gate

  • Ship the harness as a single static binary (go build -o review-harness).
  • Document operator runbook (model setup, profile editing, output retention).

Acceptance Gates

Each gate must be testable. Format: command + verifiable post-condition.

  1. Reproducibility: review-harness repo . exits 0; reports/latest/repo-intake.json exists with non-zero file_count.
  2. No false positives on a clean fixture: review-harness repo tests/fixtures/clean-repo produces zero confirmed findings.
  3. Every documented static check fires on the insecure fixture: jq '[.findings[] | .check_id] | unique | length' reports/latest/static-findings.json ≥ 8.
  4. Receipts are honest about degraded phases: jq '[.phases[] | select(.status == "degraded")]' reports/latest/receipts.json lists every skipped/stubbed phase.
  5. Critical findings block production deploy: at least one critical finding is currently present; resolve before deploy.

Next Commands

  1. Open the risk register: cat reports/latest/risk-register.md
  2. Triage every critical finding; rotate any leaked credentials immediately.
  • Probe the model provider: review-harness model doctor
  • Re-run after fixes: review-harness repo /home/profit/share/local-review-harness-full-md
  • Generate the full Scrum bundle: review-harness scrum /home/profit/share/local-review-harness-full-md