security-audit

security-audit is a skill for Claude Code from DuqueOM/ML-MLOps-Portfolio. It costs 33 tokens per session (1,472 once invoked), scanned A, original, MIT.

A security check that scans code, dependencies, container images, cloud permissions, and deployment settings before a build or release.

In plain words
What is it for?
Use it to block risky builds and deployments, verify AWS or GCP workload identity, check image signing and software bills of materials, and provide evidence for security fixes.
Why use it?
It catches leaked secrets, known vulnerabilities, unsafe container practices, and overly broad cloud access before they reach production.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/duqueom/ml-mlops-portfolio/security-audit
Any agent
npx skills add DuqueOM/ML-MLOps-Portfolio --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/DuqueOM/ML-MLOps-Portfolio

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/security-audit.svg)](https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/security-audit)
Your own site
<a href="https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/security-audit"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.01472
Opus 5 $0.00016 $0.00736
Sonnet 5 $0.00007 $0.00294
Haiku 4.5 $0.00003 $0.00147

Measured 6d ago against content hash 7b780eaabc12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Check Dockerfile for anti-patterns (running as root, curl|bash, etc.)
.devin/skills/security-audit/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit Skill

Agent-SecurityAuditor runs this skill before every build and deploy. Blocks the pipeline if any critical finding is detected.

What this skill checks

1. Secret scanning (blocker)

  • gitleaks detect --no-git --source=<service-path> --redact --config=.gitleaks.toml
  • Scan last 50 commits: gitleaks detect --source=<repo> --log-opts="-50"
  • Scan env files: .env, .env.local, .envrc — must not be committed
  • Scan Terraform state: terraform.tfstate must NOT exist in repo (D-10)

Block pipeline if any finding. Chain to /secret-breach for rotation.

2. Dependency vulnerabilities (blocker for HIGH/CRITICAL)

  • trivy fs --severity HIGH,CRITICAL <service-path>
  • Check requirements.txt for known CVEs
  • Fail on any CVE with fix available (patch is mandatory)

3. Container image scanning (blocker for CRITICAL)

  • trivy image --severity HIGH,CRITICAL <image-tag>
  • Verify base image has security updates
  • Check Dockerfile for anti-patterns (running as root, curl|bash, etc.)

4. IAM least-privilege (blocker)

  • Verify service uses IRSA (AWS) or Workload Identity (GCP) — not static credentials
  • grep -rE "AWS_ACCESS_KEY_ID|AWS_SECRET_ACCESS_KEY" --include="*.py" --include="*.yaml" <service-path> must return zero hardcoded values
  • K8s ServiceAccount must have annotations.iam.gke.io/gcp-service-account (GCP) or annotations.eks.amazonaws.com/role-arn (AWS)
  • IAM policy must have Resource specified (not "*") and Condition where applicable

5. Image signing (required for prod) — keyless OIDC (D-19)

  • The template uses keyless Cosign (no static public key). Verify via:
    cosign verify <image-ref> \
      --certificate-identity-regexp 'https://github.com/ORG/REPO/.github/workflows/ci.yml@.*' \
      --certificate-oidc-issuer https://token.actions.githubusercontent.com
    
  • Unsigned images are blocked by Kyverno admission controller in prod namespace (see templates/k8s/policies/kyverno-image-verification.yaml).
  • Missing signature → block deploy, chain to CI sign_image step.
  • Do NOT use cosign verify --key <pub-key> — that pattern requires long-lived key material (D-17/D-18 violation) and is not what the Kyverno ClusterPolicy in this template expects.

Read the full file on GitHub · 135 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 135 lines · 33 tokens per session scan A 7b780eaabc12

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository DuqueOM/ML-MLOps-Portfolio (5 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,472 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.