Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Phishing Triage

    1

    Automated phishing triage and header analysis for SOC teams to detect spoofing and malicious email indicators.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Phishing Triage

    Phishing Triage

    Example session with this skill installed

    Analyze this email header for a potential phish targeting 'acme-corp.com'. The user reports an urgent password reset request from 'security-acme.com'.

    • Read your context and instructions
    • Compiled the phishing triage

    I have processed the headers provided. The analysis indicates a high-confidence phishing attempt utilizing lookalike domain spoofing and failed authentication.

    Phishing Triage Report

    AttributeValue
    SubjectUrgent: Action Required - Password Expiry for acme-corp.com
    VerdictLikely Malicious (Score: 78)
    Sender"IT Security" admin@security-acme.com
    Return-Pathbouncing-svc@attacker-relay.net
    Auth ResultsSPF=fail, DKIM=none, DMARC=fail
    Source IP192.0.2.45 (Uncategorized VPS)

    Key Findings

    • Lookalike Domain: 'security-acme.com' flagged as a high-similarity match to protected domain 'acme-corp.com'.
    • Auth Failure: DMARC policy failed; the sending IP is not authorized by the purported domain.
    • Header Mismatch: The From header domain does not match the Return-Path, indicating relay manipulation.

    Credential Theme: The message body contains high-pressure language ("account suspension") and credential-themed URL paths.

    Indicators of Compromise (IOCs)

    • Domain: security-acme.com
    • IP: 192.0.2.45
    • Defanged URL: hxxps[://]security-acme[.]com/login/reset-password?id=99283

    Next steps

    • Block the sender domain security-acme.com and source IP 192.0.2.45 at the mail gateway.
    • Purge all messages from this sender across the tenant.
    • Reset credentials for any users who clicked the link and verify MFA logs for the target accounts.

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

    About this skill

    Manual email analysis is a slow, error-prone bottleneck for SOC teams. This skill automates the forensic triage of suspicious emails by parsing raw headers and attachments to identify spoofing, authentication failures, and malicious intent. It converts raw .eml or .msg data into structured evidence for immediate incident response.

    What it does

    • Authentication auditing parses SPF, DKIM, DMARC, and ARC results to detect delivery failures.
    • Header inspection traces Received hops and flags mismatches between From, Reply-To, and Return-Path headers.
    • Spoofing detection identifies display-name deception and lookalike domain attacks using edit-distance checks.
    • URL analysis extracts links to flag mismatched anchor text, IP literals, shorteners, and punycode.
    • Attachment forensics hashes files and scans for risky extensions, double extensions, and Office macro indicators.
    • Scored reporting generates a SOC-ready verdict (0-50+) based on weighted heuristic findings.

    How it works

    1. Source ingestion takes raw message headers or exported email files provided by the user.
    2. Automated triage runs the included Python scripts to extract indicators and calculate the threat score.
    3. Protected domain check compares the sender against a whitelist to identify targeted brand impersonation.
    4. Actionable response maps findings to specific containment steps like purges, blocks, or credential resets.

    Frameworks & tools

    This skill utilizes a Python-based analysis engine (eml_triage.py) and specialized reference guides for incident response. It is designed to work with standard email export formats like .eml and .msg.

    Why this beats prompting it yourself

    Prompting an LLM to "find phishing" often misses subtle header discrepancies or fails to calculate consistent risk scores. This skill uses deterministic Python scripts to verify authentication protocols and file signatures, ensuring your SOC reports are based on technical evidence rather than linguistic guesswork.

    Use cases

    • User report queues to quickly clear batches of suspicious emails reported by employees.
    • Incident write-ups to generate standardized tickets for tracking and remediation.
    • Attachment screening to identify hidden macros or executable scripts in archives.
    • Brand protection to detect external actors spoofing company executives or domains.

    Known limitations

    Analysis quality depends on providing original headers; forwarded emails lose critical routing data. The script requires a Python 3 environment to execute the triage logic.

    Requires original .eml or .msg files for full header fidelity. Analysis logic requires a Python 3 environment. Score is a triage aid, not a definitive guarantee of safety.

    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 any payment.

    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 1 month ago

    Permissions

    Terminal / Shell
    Listed1 month ago
    Updated28 days ago

    What's inside

    Frequently Asked Questions

    This skill is designed for use with AI agents capable of executing Python scripts. It is compatible with major platforms that support tool-use or 'Code Interpreter' environments, allowing the agent to run the triage engine locally.

    You must provide the raw email source (such as an .eml or .msg file) or the full message headers. Forwarded emails are not recommended, as they often strip away the critical routing and authentication data needed for accurate spoofing detection.

    You will receive the proprietary Python-based analysis engine (`eml_triage.py`), a set of specialized incident response reference guides, and the integration logic for your AI agent to interpret the scoring results.

    Unlike generic prompts that rely on an LLM's 'best guess,' this skill uses a deterministic Python engine to perform technical verification of SPF/DKIM/DMARC records and header hops, ensuring your SOC reports are based on forensic facts.

    The skill includes a 'Protected Domain' configuration file. By adding your company's primary domains and executive names to this list, the engine can specifically flag lookalike domains and display-name deception targeting your brand.

    New in Security