Przejdź do treści
Biblioteka skilli
Bezpieczeństwo · Przegląd i audyt

dependency-audit

/dependency-audit

Sprawdza zależności pod kątem CVE, obowiązków licencyjnych, przestarzałych pakietów i ryzyka łańcucha dostaw, według metody opartej na dowodach i dobranej do ekosystemu.

Licencja
MIT
Ostatnia zmiana repozytorium
27.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
6
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Sprawdza zależności pod kątem CVE, obowiązków licencyjnych, przestarzałych pakietów i ryzyka łańcucha dostaw, według metody opartej na dowodach i dobranej do ekosystemu.

Oryginalny opis (EN)

Evidence-first dependency audit method: per-ecosystem tool matrix, license obligation model and supply-chain signal catalog. TRIGGER WHEN: auditing dependencies for CVEs, license obligations, outdated packages or supply-chain risk; the audit method in references/audit.md is run by /daodan:check-health and by the dependency perspective of /daodan:review-changes and /daodan:review-branch. DO NOT TRIGGER WHEN: dead-code or unused-dependency removal (use senior-review:application-cleanup-method or typescript-development:knip), or code-level security review (use senior-review:security-auditor).

Jak działa

  1. Core principles
  2. References
Sekcje z nagłówków SKILL.md, w oryginale · 96 linii, 990 słów
Podgląd SKILL.md
---
name: dependency-audit
description: >
  Evidence-first dependency audit method: per-ecosystem tool matrix, license obligation model and supply-chain signal catalog.
  TRIGGER WHEN: auditing dependencies for CVEs, license obligations, outdated packages or supply-chain risk; the audit method in references/audit.md is run by /daodan:check-health and by the dependency perspective of /daodan:review-changes and /daodan:review-branch.
  DO NOT TRIGGER WHEN: dead-code or unused-dependency removal (use senior-review:application-cleanup-method or typescript-development:knip), or code-level security review (use senior-review:security-auditor).
---

<daodan_host_binding host="codex">
This binding governs execution of this package and its loaded references. It takes
precedence over executable examples written for another host. Use only registered
tools and their actual input schema; an example never creates a tool, argument,
permission, model alias or nested worker capability. Preserve the generated worker
allowlist, dependency closure, scope and delivery contracts.

Codex binding: the adapter binds repository read to read_file, writes to
apply_patch and shell execution to shell; use the equivalent registered tools of
the active Codex runtime and their actual fields. In particular, a shell example's
command, timeout and background fields are not automatically another runtime's
cmd, yield_time_ms or session controls.
Start the runtime's available isolated subagent mechanism with the complete
rendered role body in its task prompt. Role Markdown and generated dispatch bodies
are resources, not registered skills or a native role/subagent_type parameter.
Use only declared role bindings and report an unavailable isolation mechanism.
Load installed skills by their advertised exact IDs; workflow skills carry the
<workflow>-workflow suffix. Named-agent examples do not override inline delivery.
Required foreign providers use Codex's marketplace/install commands:
codex plugin marketplace add <source>, then codex plugin add <provider>@<marketplace>.
Register plugin-declared MCP servers through the active host's MCP configuration
using the generated server command. Do not assume registration makes every tool
available to a restricted worker.
Inherit the active session's model and default variant. A source model alias such
as sonnet is not a portable override; request a different model only through an
explicit adapter mapping to a valid host identity and user authorization.

The executing agent and its coordinator own continuation, recovery, verification
and delivery. Skills supply knowledge and method instructions; they are not
executors or a runtime persistence mechanism.

Resolve each component by kind and exact installed identity. A role is dispatched
as a worker, a skill loads instructions, and a workflow starts its declared method.
Kernel owner-qualified skill references are logical provider identities: resolve
them to the actual host registry name and verified installed provider path. Do not
invent a registry string by adding an owner's prefix when the host does not use it.
Do not load an agent identity as a skill or execute a workflow name as a shell
command. Declared required foreign providers remain mandatory. If a required
provider or capability (including required MCP access or isolation) is unavailable,
stop its dependent phase and report the missing capability. Optional external
providers follow the method's declared selection and absence behavior; their
absence alone does not block the base workflow. Report any explicitly requested
but unavailable provider contribution as unfulfilled and continue independent
work. Do not install a different host's plugin or
substitute unrelated skills to claim coverage.

Shell execution alone does not establish interactive stdin. Before a capture or
checkpoint, use an available session-control mechanism. When stdin is unavailable,
keep user-driven capture in a supported background process with bounded output and
an explicit stop signal controlled by the coordinator after the user's completion
message. Close owned browser/process resources on completion or cancellation.

Continue working within the current authorization while the requested result is
achievable. After a tool error, inspect its cause, correct the relevant input or
implementation, retry when justified and verify the outcome; never repeat a
failing action blindly. Do not close the turn with a promise or a partial result
when an authorized next step can still produce or verify the requested result.
Stop only for a documented real impediment, a missing required capability, an
unresolved human decision or the caller's stop request. At that boundary, report
completed results, remaining work and the concrete prerequisite for continuation;
continue any independent work that the blocker does not prevent.

A tool's successful exit, a worker stop or an idle session is not the deliverable.
Return final text naming observed findings, artifact paths, executed checks and
blockers. An empty worker result is missing delivery: inspect or resume that worker
when permitted, or record failure. Verify required artifacts and candidate gates
before marking the requested outcome complete.

This is an execution binding, not a rewrite of source examples. Preserve programming
language fences, domain code and host APIs that are the subject of marketplace-ops
or agent-sdk-builder. A host-as-subject API is not a tool provided to this session.
Compiled binding and static checks do not prove an installed host executed a run.
</daodan_host_binding>

# Dependency Audit Knowledge Base

Method for auditing third-party dependencies without inventing facts. `references/audit.md` orchestrates the audit; the other references hold the depth, loaded on demand.

## Core principles

1. **Tool-first.** The audit runs the ecosystem's own tooling and reads registries and advisory databases (OSV, GitHub Advisories, RustSec, PyPA). It never re-implements a scanner in pseudo-code and never guesses what a tool would have said.
2. **Evidence tiers.** Every reported fact is `TOOL-REPORTED`, `INFERRED` (with the derivation stated), or `UNKNOWN` (with what would resolve it). Fabricated quantities of any kind are forbidden: no estimated hours, no invented percentages, no dollar figures.
3. **Non-destructive remediation.** Never `--force`, never unapproved major-version upgrades, never lockfile regeneration, never dependency replacement without first presenting the proposed change, its compatibility risk, and a test/rollback plan.
4. **Licenses are obligations, not a matrix.** License analysis asks what obligations a dependency's license imposes given how the project combines and distributes it. Binary "X is incompatible with Y" tables are wrong often enough to be banned.
5. **Honest coverage.** Missing tools and unreachable registries are reported as gaps, with install commands, instead of being papered over.

## References

| File | Load when |
|---|---|
| `references/audit.md` | Running the audit for a caller: target forms, ecosystem, depth and license decisions, the update authorization, the workflow steps and the report format |
| `references/ecosystems.md` | Selecting or running audit / outdated / license tooling for any ecosystem, or parsing its output |
| `references/license-analysis.md` | Writing any license finding, classifying an SPDX identifier, or answering a copyleft question |
| `references/supply-chain.md` | Evaluating supply-chain risk signals or reviewing a dependency diff for tampering |
Pliki w paczce (6)
  • SKILL.md 7 KB
  • SKILL.toml 1 KB
  • references/audit.md 14 KB
  • references/ecosystems.md 11 KB
  • references/license-analysis.md 9 KB
  • references/supply-chain.md 9 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · acaprino/alfio-claude-plugins100MIT
acaprino/alfio-claude-plugins100MIT
acaprino/alfio-claude-plugins100MIT
acaprino/alfio-claude-plugins100MIT
acaprino/alfio-claude-plugins100MIT
OKHP3/skillz100MIT
mathews-tom/armory100MIT
meyshad/skillforge100MIT
tansuasici/claude-code-kit100MIT

Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.

Migawka bazy z 13.11.2026 · wersja paczki cd813bb5b6b6 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100dependency-vulnerability-audit
    Wykonuje audyt bezpieczeństwa łańcucha dostaw skanerami CLI, kontrolą zgodności licencji i oceną ryzyka dostawców zależności pod kątem znanych CVE.
  • 100analyze-dependencies
    Audytuje zależności projektu pod kątem ryzyka: podatności, zdrowie pakietów i ryzyko łańcucha dostaw.
  • 100code-dep-audit
    Audytuje zależności pod kątem podatności bezpieczeństwa, przestarzałych pakietów i zgodności licencji, przy kontroli łańcucha dostaw, przygotowaniu wydań i reakcji na CVE.
  • 100iblai-vibe-security-dependency-audit
    Audytuje zależności, frameworki i narzędzia projektu pod kątem znanych podatności, CVE i antywzorców bezpieczeństwa, w tym ryzyk łańcucha dostaw i przestarzałych pakietów.
  • 90dependency-management-deps-audit
    Sprawdza zależności projektu pod kątem znanych podatności, licencji, przestarzałych pakietów i ryzyka łańcucha dostaw, z planem napraw.
  • 100supply-chain-audit
    Sprawdza ryzyko łańcucha dostaw zależności przy zmianie plików z pakietami, np. package.json lub go.mod.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.