● Deploy anywhereGet API key

Home / Add-ons / Security Audit Pack

Security Audit Pack — a source-first review workflow for coding agents

Short answer. 14 audit chapters, a report schema, two validators, a framework mapping, a report template, and a code review toolkit with a deterministic diff check and OSV dependency report. Built for source-code review, not a penetration test or live scan.

$49

one-time payment · no renewal · commercial licence included

$49 — buy onceInstant download after payment

USD. If the file does not download, contact support for a replacement or a refund.

See before you buy

Version 2026-11 · 53 files · 187.5 KB. SHA-256 2c5dca21e2261e1fac0c33e8257245a09f8c30de0c115c7b64ee1b48eab707cd.

The ZIP contains 14 chapter files plus a SKILL.md entry point, the report schema, two validators, the framework mapping, the report template, the MIT licence and the code review toolkit.

File list (53 files)
  • FRAMEWORK-MAPPING.md
  • LICENSES/security-audit-skill-MIT.txt
  • README.md
  • REPORT-TEMPLATE.md
  • RUN-LOG.txt
  • code-review/CHECKLIST.md
  • code-review/LICENCE.txt
  • code-review/README.md
  • code-review/REPORT-TEMPLATE.md
  • code-review/RUN-LOG.txt
  • code-review/THIRD_PARTY_NOTICES.md
  • code-review/eslint.config.mjs
  • code-review/patches/node-api-clean.patch
  • code-review/patches/node-api.patch
  • code-review/patches/python-api-clean.patch
  • code-review/patches/python-api.patch
  • code-review/prompts/build_prompt.py
  • code-review/prompts/llm-reviewer.md
  • code-review/prompts/mock-response.json
  • code-review/prompts/request-example.json
  • code-review/prompts/schema.json
  • code-review/prompts/system.txt
  • code-review/qa/README.md
  • code-review/qa/controls-last-run.md
  • code-review/qa/last-run.md
  • code-review/qa/run_controls.py
  • code-review/qa/run_qa.py
  • code-review/real-prs/manifest.json
  • code-review/real-prs/results-v2.json
  • code-review/review.py
  • code-review/reviews/REAL-PR-EVAL-V2.md
  • code-review/sca.py
  • skill/AI-AND-LLM.md
  • skill/ATTACK-CLASSES.md
  • skill/CLIENT-SIDE.md
  • skill/CLOUD-AND-DEPLOYMENT.md
  • skill/DATA-ISOLATION-AND-LIFECYCLE.md
  • skill/DESKTOP-MOBILE-AND-LOCAL-IPC.md
  • skill/HUNTING.md
  • skill/MEMORY-SAFETY-AND-BINARY.md
  • skill/PROTOCOLS-RPC-AND-MESSAGING.md
  • skill/RECONNAISSANCE.md
  • skill/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md
  • skill/SKILL.md
  • skill/SUPPLY-CHAIN-AND-RELEASE.md
  • skill/UPSTREAM-README.md
  • skill/VALIDATION-AND-REPORTING.md
  • skill/WEB-PROTOCOL-AND-AUTH.md
  • skill/report-schema.json
  • skill/validate-coverage-ledger.cjs
  • skill/validate-coverage-ledger.test.cjs
  • skill/validate-findings.cjs
  • skill/validate-findings.test.cjs

The finding below is illustrative, not from a live test.

On this page · 15 sections
  1. Who it is for
  2. The problem it removes
  3. What you get
  4. How to use it
  5. What is in the pack
  6. The 14 chapters
  7. A sample finding
  8. What the validators reject
  9. Included: deterministic diff check and dependency report
  10. How it compares to a scanner
  11. What it is not
  12. How a review runs
  13. Why the framework mapping is labelled “indicative”
  14. What it costs and who it is for
  15. Licence

Who it is for

Engineering teams and consultancies reviewing repositories they own or are authorised to assess.

The problem it removes

What you get

How to use it

1. Download and unzip

The ZIP contains the skill directory, the mapping, the template and the licence.

2. Run a guidance review

Ask your agent for a read-only trust-boundary review first; no file writes, no execution.

3. Validate the report

Run the two Node validators against findings.json; both are dependency-free.

curl -sS https://plugsky.com/api/addons/security/pack.zip \
  -H "Authorization: Bearer $PLUGSKY_SESSION" \
  -o plugsky-security-audit-pack.zip

What is in the pack

The pack is a working directory, not a slide deck. Your agent reads the chapters, applies the workflow to a repository, and writes findings against a schema the validators can check.

Contents of the ZIP.
PartWhat it doesWhy it matters
14 chapters + SKILL.mdReconnaissance, attack classes, web/auth, protocols, client-side, cloud, data isolation, supply chain, memory/binary, resource exhaustion, AI/LLM, desktop/mobile, hunting, reportingCovers the boundaries a generic checklist misses
report-schema.jsonRequired fields for every findingA finding without a boundary and evidence fails the schema
Two validatorsDependency-free Node scripts for findings and coverageCatches empty claims before a report ships
Framework mappingIndicative MITRE ATT&CK, NIST 800-53, SOC 2 referencesGives reviewers the language they ask for
Report templateBoundary, principal, evidence, reproduction, fix, priorityTurns an agent's notes into a reviewable document
Code review toolkitreview.py (diff rules), sca.py (OSV advisories), prompts and a checklistA reproducible diff check and dependency report alongside the audit workflow

The 14 chapters

Grouped for orientation; each chapter is a standalone file.
GroupChaptersTypical source-review finding
Entry and identityReconnaissance, web protocol and auth, protocols/RPC/messagingAuth bypass, IDOR, token confusion
Data and executionData isolation and lifecycle, memory safety and binary, resource exhaustionCross-tenant read, command injection, unbounded allocation
Platform and supply chainCloud and deployment, supply chain and release, client-side, desktop/mobile and local IPCPublic bucket, dependency confusion, insecure IPC
AppliedAI and LLM, hunting, validation and reporting, attack classesPrompt injection, missing evidence, unvalidated severity

A sample finding

Illustrative finding; not from a live test.

{
  "id": "SEC-001",
  "title": "Tenant A can read Tenant B invoices by changing the id",
  "severity": "high",
  "boundary": "tenant",
  "principal": "authenticated tenant A user",
  "resource": "tenant B invoice records",
  "evidence": ["app/Http/InvoiceController.php:84-96"],
  "reproduction": "fixture tenants A and B; request B's invoice id with A's session",
  "fix": "scope the query by workspace_id from the session, not the path id",
  "frameworks": [{"name": "NIST 800-53", "ref": "AC-3"}],
  "status": "confirmed"
}

That shape is deliberate: a reviewer can read the boundary, check the file, repeat the reproduction, and apply the fix without a meeting. A finding that cannot fill these fields is a needs-validation item, not a confirmed one.

What the validators reject

The 34/34 and 31/31 results are unit tests for the two validators. They show the checks behave as specified; they are not a measure of audit coverage or a guarantee that a repository is secure.

Included: deterministic diff check and dependency report

The pack now includes a small code review toolkit in code-review/. review.py parses a unified diff, maps added lines to new-file line numbers and runs 12 fixed rules. Tests, docs, fixtures, examples, vendor and generated files are classified as non-production and kept out of scored findings. Every scored finding carries a rule id, a file and line, and a remediation.

sca.py reads a changed package-lock.json, requirements.txt, go.mod or pom.xml and asks the free OSV.dev batch API for known advisories. It is a dependency report, not a reachability proof: a matching version is a prompt to investigate, not a confirmed exploit.

The toolkit also carries an LLM review prompt, a JSON schema, a human checklist and a report template. The defaults are deliberately conservative. On 20 merged pull requests from four permissive repositories (3,755 changed lines), the diff rules emitted 0 scored findings; 25 observations in tests and docs were excluded as non-production. The OSV positive control caught axios #11410 (follow-redirects@1.16.1, CVE-2026-116689). A zero-finding run is not evidence that a repository is secure.

This is not a hosted reviewer. There is no webhook, no auto-merge and no repository code execution. It is a local workflow that produces an artifact a reviewer can check.

How it compares to a scanner

A scanner reports patterns. This workflow reports a boundary violation with a principal, a resource and a path. That difference changes the output: a scanner can produce two hundred rows in a minute and none of them tell a reviewer whether the issue is reachable in this deployment. The pack forces the reachability question before a finding is confirmed.

It also changes the false-positive economics. A scanner's noise is cheap to generate and expensive to triage. The evidence requirement here is deliberately strict: file and line, the configuration that makes the path live, and a safe reproduction with fixtures. If any of those is missing, the item is marked needs validation rather than counted as a finding. A report with ten confirmed findings and four open questions is more useful than one with sixty rows and no owner.

The trade-off is time. A guided review of a service takes hours, not seconds, and it depends on the reviewer's judgement. The pack is not a replacement for a scanner; it is the layer that decides which scanner output matters and what to do next.

What it is not

It is a defensive, source-first code review. It does not scan a live service, test availability, or run a penetration test. The workflow explicitly requires a sandbox before any target-controlled code executes, and reports a missing sandbox as a blocker instead of improvising one.

That boundary is the product. A pack that promises a pentest creates a liability; a pack that produces evidence-backed source findings creates a review.

How a review runs

  1. Scope. Name the repository, the commit, and the trust boundaries that matter: tenant, user, process, network, model context.
  2. Guidance first. Ask for a read-only review of one module. No writes, no execution, no report directory.
  3. Evidence. Every candidate finding must name the principal, the resource, the file and line, and the path that makes it reachable.
  4. Validate. Run node validate-findings.cjs findings.json. A finding that fails the schema is not ready.
  5. Report. Use the template. Separate confirmed findings from needs-validation items.

The pack ships with the upstream skill's own tests. We ran both validators before shipping: 34/34 and 31/31 pass. The run log is in the ZIP.

Why the framework mapping is labelled “indicative”

MITRE ATT&CK is a behavioural model. NIST 800-53 and SOC 2 are control models. There is no one-to-one crosswalk, and a finding that maps to a control does not make a system compliant. The mapping exists so a reviewer can find the right conversation, not so a report can claim an audit opinion.

What it costs and who it is for

It is $49 once. It earns its price when a team reviews repositories repeatedly and wants the same structure each time: an agency doing pre-delivery reviews with the client's authorisation, a platform team reviewing a service before launch, or a maintainer preparing a security questionnaire response. It is not a substitute for a specialist when the system is high-risk, and it is not legal advice.

Licence

The audit skill is MIT, copyright Cloudflare, Inc. The licence text is in LICENSES/. Plugsky is not affiliated with Cloudflare and does not imply endorsement. Our framework mapping and report template are original and may be used inside your organisation on repositories you own or are authorised to review; they may not be resold as a standalone product.

Questions

What exactly do I get?

A ZIP with 14 audit chapters, report-schema.json, two validators, a framework mapping, a report template, the MIT licence, and a code review toolkit: deterministic diff check, OSV dependency report, prompts and checklist.

Is this a penetration test?

No. It is a defensive, source-first code review. It does not scan live systems, probe endpoints or test availability.

Which agent does it work with?

Any agent that reads a directory of skills: Claude Code, Codex, Cursor, Gemini CLI, OpenCode. The validators need Node.

Are the validators tested?

Yes. The validators pass 34/34 and 31/31 unit tests; the run log is in the ZIP. Those results cover the validators, not the depth of an audit.

Can I use it commercially?

Yes, inside your organisation on repositories you own or are authorised to review. Resale of the pack itself is not permitted. Agencies should contact us for client-repository terms.

Sources

Prompt Cost Linter

Static analysis for seven LLM cost anti-patterns: full context resent every turn, missing prompt caching, flagship models on simple tasks, unbounded output, retry storms, batchable loops and needless re-embedding.

$19/month · Read more →

Prompt Pack

Forty production prompts across extraction, classification, support and coding, each with a fixed output shape, two or more eval cases and a runner that checks them against the API.

$49/one-time · Read more →

Buy once, download immediately

Stripe checkout. The download appears on this page and in Dashboard → Billing → Add-ons as soon as payment completes.

$49 — buy onceCompare add-ons

Planning a budget first? The Flat-Rate AI Budget Book 2027 is a free 14-page workbook. Buyers can inspect sample deliverables.