agentsclimarketplace

Security

Skill mj-deving/pai-skills/skills/Security

Curated, sanitized export of 21 agent-skill packages for Claude Code and Codex, gated by an automated publication audit (no secrets, no local paths).

Install
npx -y skills add mj-deving/pai-skills --skill Security

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 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.

What its author says it does

Copied from the file, not written here

Security assessment — network recon, web app testing, prompt injection testing, security news, and vulnerability scanning. USE WHEN recon, port scan, subdomain, DNS, WHOIS, pentest, threat model, OWASP, prompt injection, LLM security, security news, trivy, CVE, vulnerability scan, sops, encrypt secrets.

SKILL.md

3.4 KB, as published. Nobody here has run it

Security

Unified skill for security assessment and intelligence workflows.

Workflow Routing

Request PatternRoute To
Recon, reconnaissance, port scan, subdomain, DNS, WHOIS, ASNRecon/SKILL.md
Web assessment, OWASP, pentest, ffuf, app security, threat modeling, STRIDE, DREAD, PASTA, threat modelWebAssessment/SKILL.md
Prompt injection, jailbreak, LLM security, guardrail bypassPromptInjection/SKILL.md
Security news, sec updates, breaches, tldrsec, security researchSECUpdates/SKILL.md
Annual reports, security trends, threat landscape, vendor reportsAnnualReports/SKILL.md
Secure coding, vulnerability prevention, defense patterns, security review codeSecureCoding/SKILL.md
Supply chain, dependency audit, package security, new dependency checkSupplyChain.md
Secret audit, scan for secrets, find leaked keys, git history secretsSecureCoding/SKILL.md
Trivy, vulnerability scan, CVE, container scan, IaC scanSee Trivy Vulnerability Scanning below
sops, encrypt secrets, decrypt secretsSee sops Secrets Management below

Trivy Vulnerability Scanning

Scan projects, containers, and infrastructure-as-code for known vulnerabilities.

# Scan project directory for CVEs
trivy fs --format json . | jq '.Results[] | select(.Vulnerabilities) | .Vulnerabilities[] | select(.Severity == "CRITICAL")'

# Scan container image
trivy image --format json myapp:latest

# Scan IaC (Terraform, CloudFormation)
trivy config --format json ./infrastructure/

# CI gate — fail on critical
trivy fs --exit-code 1 --severity CRITICAL .

When to use:

  • Before deploying — scan the project for known CVEs
  • Container builds — scan images before pushing to registry
  • IaC review — catch misconfigurations in Terraform/CloudFormation before apply
  • CI pipelines — add --exit-code 1 to fail the build on critical findings

Triage approach:

  1. Run trivy fs --format json . to get full results
  2. Filter to CRITICAL and HIGH severity first
  3. Check if vulnerable code paths are actually reachable
  4. Update dependencies where possible, document accepted risks where not

sops Secrets Management

Encrypt and decrypt secrets files using Mozilla sops with age keys.

# Encrypt a file with age key
sops --encrypt --age age1... secrets.yaml > secrets.enc.yaml

# Decrypt
sops --decrypt secrets.enc.yaml

# Edit encrypted file in place
sops secrets.enc.yaml

When to use:

  • Storing secrets in git — encrypt with sops so they can be version-controlled safely
  • Sharing secrets across team/agents — encrypted files can be committed and shared
  • Rotating secrets — edit in place with sops secrets.enc.yaml

Rules:

  • Never commit unencrypted secrets files
  • Use age keys (not PGP) for new setups — simpler key management
  • Store the age key outside the repo (e.g., ~/.config/sops/age/keys.txt)

Examples

Example 1: User: "[typical request]" → Routes to appropriate sub-skill workflow

Example 2: User: "[another request]" → Routes to different sub-skill workflow

Keep looking

Skills are one crate of 328,083. 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.