More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AppSec, Cloud and Devices

    1

    Protect APIs, containers, email, mobile, IoT, OT and identity fraud. 10 ordered skills, starting with DevSecOps, Container and Kubernetes Security, API Security.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AppSec, Cloud and Devices

    AppSec, Cloud and Devices

    Example session with this skill installed

    Fictional company "Northwind Parcels" (12 developers, 6 repos in Python and TypeScript, GitHub-style CI, deploys containers weekly). Today only a dependency alert email exists; a scanner backlog from a past trial has about 300 untriaged findings (invented figure for this exercise).

    • Read your context and instructions
    • Compiled the appsec cloud

    DevSecOps Assessment: Northwind Parcels (fictional)

    Lifecycle Coverage: Plan - no threat modeling (gap) -> add trigger-based modeling. Code - none -> secret detection pre-commit. Build - no SBOM, floating base images -> pin digests, generate SBOM. Test - none -> SAST/SCA on PR; DAST on staging in phase 3. Release/Operate - no image scan, no intake process -> registry scan, vulnerability intake owner.
    Pipeline Gate Policy: Secrets: block, no exception except documented test fixtures. SCA critical with reachable path: block after 4-week warn period. SAST: warn only until false-positive rate reviewed. IaC misconfiguration: block on public storage and open admin ports.
    Roadmap: 1) Rotate and scope CI tokens (S, high risk reduction). 2) Secret scanning (S). 3) SCA and SAST in warn mode on pilot repo (M). 4) Baseline backlog and assign owners (M). 5) Enforce gates repo by repo (M).
    Pipeline Hardening Findings: long-lived write tokens (high); unpinned actions (medium); fork builds with secrets access (high).
    Triage and SLA Proposal: due dates by severity and exposure, set by the team; exceptions need approver and expiry.
    Assumptions: scanner choice open; thresholds are team decisions.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Product security often need a repeatable process, not a one-off prompt. This pack targets: Protect APIs, containers, email, mobile, IoT, OT and identity fraud.

    What's inside (10 skills, suggested learning order)

    1. DevSecOps — Integrate security into the development lifecycle.
    2. Container and Kubernetes Security — Protect clusters.
    3. API Security — Protect APIs.
    4. Email Security and Anti-Phishing — Reduce email fraud.
    5. Payment and E-commerce Fraud Prevention — Reduce chargebacks and checkout fraud.
    6. Security GRC — Security governance, risk and compliance.
    7. OT/ICS Security — Protect operational technology.
    8. IoT Security — Protect connected devices.
    9. Mobile Security — Protect mobile apps.
    10. Deepfakes and Identity Fraud — Combat synthetic identity.

    Why a skill pack instead of a one-off prompt

    Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.

    How to use

    1. Install the pack in your SKILL.md-compatible agent.
    2. Ask for the task in plain language (for example: "integrate security into the development lifecycle").
    3. Review the output against the skill's quality checks before using it.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Outputs are drafts that need human review; they are not professional, legal or financial advice. Tools, APIs and prices change; check current vendor documentation before relying on version-specific details. Quality depends on the context you give the agent (data, requirements, constraints). Instruction-only skills: they produce documents and plans, not running software.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Permissions

    No special permissions declared or detected

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    10 skills, each with SKILL.md and references/sources.md: DevSecOps; Container and Kubernetes Security; API Security; Email Security and Anti-Phishing; Payment and E-commerce Fraud Prevention; Security GRC; OT/ICS Security; IoT Security; Mobile Security; Deepfakes and Identity Fraud.

    Product security.

    Agents that read the SKILL.md format. See the Compatibility note for what was actually tested.

    New in Security