agentsclimarketplace

Dependency audit

Skill Wilder1222/superomni/skills/dependency-audit

Dependency security, license, and freshness audit. Dispatches dependency-auditor agent to scan all package managers. Triggers: "dependency audit", "check dependencies", "npm audit", "security scan", "check for vulnerabilities", "outdated packages", "license check".From its SKILL.md

Install
npx -y skills add Wilder1222/superomni --skill dependency-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

7.4 KB, as published. Nobody here has run it

<!-- Inlined into every SKILL.md via {{PREAMBLE_CORE}}. Keep ≤30 lines. -->

Preamble (Core)

Status protocol — end every session with one of: DONE (evidence provided) · DONE_WITH_CONCERNS (list each) · BLOCKED (state what blocks you) · NEEDS_CONTEXT (state what you need).

Auto-advance — pipeline: THINK → PLAN → REVIEW → BUILD → VERIFY → RELEASE. Only human gate is spec approval at THINK. On DONE at other stages, print [STAGE] DONE -> advancing to [NEXT-STAGE] and invoke the next skill. On any non-DONE status at any stage, STOP.

Output directory — all artifacts go in docs/superomni/<kind>/<kind>-[branch]-[session]-[date].md. See CLAUDE.md for the full directory map.

TACIT-DENSE — before high-tacit decisions, classify D1 (domain expertise) · D2 (user-facing UX) · D3 (team culture) · D4 (novel pattern). On hit, output TACIT-DENSE [D#]: [question] — My default: [recommendation]. See reference for actions.

Anti-sycophancy — take a position on every significant question. Name flaws directly. No filler ("that's interesting", "you might consider", "that could work").

Telemetry (local only) — at session end, log bin/analytics-log. Nothing leaves the machine.

See preamble-ref.md for detailed protocols.

Dependency Audit

Goal: Systematically audit all project dependencies for security vulnerabilities, license compliance, and staleness — then produce an actionable remediation plan.

Iron Law: No P0 CVEs Before Deploy

A dependency with a known critical CVE and an available fix is a P0 blocker. No exceptions. The deployment gate is VERDICT: APPROVED from the dependency-auditor report.

Good Example (Proper Audit Gate)

Production Readiness check includes dependency audit
dependency-auditor finds: [email protected] — CVE-2022-24999 (critical) — fix: [email protected]
Action: npm update [email protected] → re-audit → APPROVED
Deploy proceeds

Bad Example (AVOID)

"Audit passed last month, skip for now"
[VIOLATED: CVEs are disclosed daily — audit must happen before every deploy]

Phase 1: Package Manager Discovery

Identify all dependency manifests in the project:

# Find all package manifests
echo "=== npm/node ==="
find . -name "package.json" -not -path "*/node_modules/*" | head -5

echo "=== python ==="
find . \( -name "requirements*.txt" -o -name "Pipfile" -o -name "pyproject.toml" \) \
  -not -path "*/.git/*" | head -5

echo "=== go ==="
find . -name "go.mod" -not -path "*/.git/*" | head -3

echo "=== ruby ==="
find . -name "Gemfile" -not -path "*/.git/*" | head -3

echo "=== rust ==="
find . -name "Cargo.toml" -not -path "*/.git/*" | head -3

echo "=== java ==="
find . \( -name "pom.xml" -o -name "build.gradle" \) -not -path "*/.git/*" | head -3

Record what was found:

PACKAGE MANAGERS FOUND
────────────────────────────────────────
npm:    [manifest files found | none]
pip:    [manifest files found | none]
go:     [manifest files found | none]
ruby:   [manifest files found | none]
rust:   [manifest files found | none]
java:   [manifest files found | none]
────────────────────────────────────────

Phase 2: Dispatch planner-reviewer Agent (Security Audit, Dependency Mode)

Dispatch the planner-reviewer agent in security audit mode (dependency sub-mode) with:

  • The list of all package manifests found in Phase 1
  • Explicit instruction to run Phase 4: Dependency Audit (OWASP A06) and skip code scanning
  • The production context (pre-deploy or routine audit?)

The agent will:

  1. Run CVE scans across all discovered package managers (npm audit, pip-audit, cargo audit, etc.)
  2. Classify findings by severity (P0/P1/P2/P3)
  3. Return a SECURITY AUDIT REPORT focused on the DEPENDENCIES (OWASP A06) section with verdict APPROVED / APPROVED_WITH_NOTES / CHANGES_REQUIRED

Handoff:

  • APPROVED → proceed to Phase 3 summary
  • APPROVED_WITH_NOTES → note P1/P2 findings for next sprint backlog
  • CHANGES_REQUIRED → P0 CVEs found; apply remediation commands before re-auditing
  • BLOCKED → package manager tools not available; install tools and retry

Phase 3: Triage Findings

For each finding returned by the agent:

Security Triage

SeverityActionTimeline
P0 Critical (CVSS ≥ 9.0)Block deploy; fix immediatelyBefore any deployment
P1 High (CVSS 7-8.9)Fix before next releaseWithin current sprint
P2 Medium (CVSS 4-6.9)Fix if easy; backlog if notWithin next 2 sprints
P3 Low (CVSS < 4)BacklogOpportunistic

License Triage

License typeAction
GPL/AGPL in productionLegal review required before deploy
Unknown licenseLegal review required
LGPL (dynamic link only)Usually OK — confirm with legal
MIT/Apache/BSD/ISCNo action needed

Phase 4: Apply P0 Remediation

For each P0 finding, apply the exact remediation command from the agent's report:

# Example npm remediations (agent will provide actual commands)
# npm update vulnerable-package@safe-version
# npm audit fix --force  (only if agent recommends)

# Verify fix applied
npm audit 2>&1 | grep -E "critical|high" | head -10

After applying remediations, re-run the test suite:

npm test 2>&1 | tail -10

If tests fail after upgrade → the dependency has a breaking change. Escalate to user.

Phase 5: Audit Report

DEPENDENCY AUDIT COMPLETE
════════════════════════════════════════
Scope:          [package managers audited]
Date:           [YYYY-MM-DD]

Security:
  P0 Critical: [N] — [fixed | outstanding]
  P1 High:     [N]
  P2 Medium:   [N]
  P3 Low:      [N]

License:
  Copyleft risk:   [N packages — names]
  Unknown:         [N packages — names]

Freshness:
  Major versions behind: [N packages]

Verdict:        APPROVED | APPROVED_WITH_NOTES | CHANGES_REQUIRED

Remediation applied:
  [package@version] — [CVE fixed]

Backlog items (P1/P2):
  [package] — [finding] — fix by [sprint/date]

Status: DONE | DONE_WITH_CONCERNS | BLOCKED
════════════════════════════════════════

Save Audit Artifact

mkdir -p docs/superomni/evaluations
_BRANCH=$(git branch --show-current 2>/dev/null | tr '/' '-' || echo "unknown")
_DATE=$(date +%Y%m%d)
_AUDIT_FILE="docs/superomni/evaluations/dependency-audit-${_BRANCH}-${_DATE}.md"
echo "Dependency audit saved to ${_AUDIT_FILE}"

Write the full DEPENDENCY AUDIT COMPLETE report block to $_AUDIT_FILE.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.