phishing fraud surface map

    1

    Heuristic risk scoring and surface mapping for suspicious URLs, domains, and phishing messages.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    phishing fraud surface map

    Example session with this skill installed

    Analyze this suspicious email text and URL: 'Your account is locked. Verify now at http://secure-bank-login-update.com/account'. Check for fraud indicators and provide a risk score.

    • Read your context and instructions
    • Compiled the phishing fraud surface

    I have analyzed the provided email content and URL using the heuristic scoring scripts. The scan identified multiple high-weight risk indicators related to domain structure and urgency tactics.

    Phishing Surface Map Report

    Indicator CategoryFindingRisk Weight
    Domain Analysissecure-bank-login-update.comHigh
    URL StructureUse of keywords "bank", "login", "update" in rootMedium
    Social EngineeringUrgent "account locked" narrativeHigh
    Sender AuthenticityNo headers provided for verificationNeutral
    Technical ObfuscationPlaintext HTTP (no SSL indicated in URL)Medium

    Final Risk Assessment: 82/100 (High Risk)

    Reasoning:
    The domain secure-bank-login-update.com exhibits classic typosquatting/impersonation characteristics. The combination of an urgent threat ("account locked") with a generic, keyword-stuffed domain is a statistically significant indicator of a credential harvesting attempt. The lack of HTTPS in the provided string further suggests a non-legitimate financial landing page.

    Next steps

    1. Do not click the link or provide any credentials on the destination site.
    2. Block the domain secure-bank-login-update.com at the network or DNS level.
    3. Report the URL to hosting providers or anti-phishing clearinghouses like PhishTank.

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

    About this skill

    Analyzing suspicious communications and links manually is slow and prone to human error. This skill provides a systematic heuristic assessment of URLs, domains, and message text to identify common phishing and fraud indicators.

    What it does

    • Pattern identification Scanning message text and metadata for known social engineering tactics and linguistic red flags.
    • Link analysis Evaluating URLs and domains for obfuscation, typosquatting, and structural anomalies.
    • Heuristic scoring Generating a risk weight based on transparent indicators rather than black-box algorithms.
    • Operational reporting Delivering structured summaries that explain the "why" behind a specific risk level.

    How it works

    1. Ingest indicators The user provides the raw message content, suspicious URLs, or domain names for evaluation.
    2. Scan inputs The skill runs scan_inputs.py to extract specific indicators from the provided data.
    3. Calculate risk The risk_score.py script aggregates findings into a categorized score.
    4. Generate report The agent outputs a final assessment including evidence and suggested mitigation steps.

    Frameworks & tools

    The skill utilizes custom Python logic for string analysis and heuristic weighting. It runs locally via Bash commands to ensure data privacy without external API dependencies.

    Why this beats prompting it yourself

    Standard LLM prompts often hallucinate security risks or miss subtle technical indicators like homograph attacks. This skill forces the agent to follow a strict heuristic scoring model, ensuring consistent results that don't rely on the model's subjective "gut feeling."

    Use cases

    • Email triage Initial screening of suspicious internal reports before escalation to a SOC.
    • URL verification Checking shortlinks or redirected domains for structural red flags.
    • Fraud detection Analyzing SMS or chat messages for common financial scam patterns.

    Known limitations

    This tool does not perform actual malware sandboxing or dynamic analysis. It relies entirely on the quality of provided input and should not replace enterprise-grade security suites.

    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.

    No malware sandboxing or dynamic execution. Heuristic-only analysis. Results depend on input completeness. Not a replacement for enterprise SOC tools.

    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

    Terminal / Shell
    Read Files
    Write Files

    Allowed Hosts

    {item}
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a structured, heuristic analysis of links and messages to detect fraud, offering consistent risk scoring that eliminates the subjective 'hallucinations' or missed technical flags common in standard LLM prompts.

    You will receive the core logic scripts (Python-based), a standardized risk scoring framework, and the bash-ready workflow for local execution.

    Since the skill runs locally via Python and Bash, your sensitive communication data and URLs are processed on your own infrastructure rather than being sent to external third-party security APIs.

    This skill is designed to be agent-agnostic; it can be integrated into any AI agent or workflow capable of executing Python scripts and processing structured text output.

    No, this is a static analysis tool that evaluates structural and linguistic indicators; it does not execute code, visit live sites, or perform dynamic malware sandboxing.

    New in Security