Works with the AI Agents you already use
Cybersecurity-Prompt-Guard-Pack
Automated toolkit for Google SecOps, cloud security remediation, OSINT reconnaissance, and LLM safety testing.
$10
Cybersecurity-Prompt-Guard-Pack
Example session with this skill installed
Run a passive OSINT scan on example.com and check for subdomains and SSL certificate expiry.
- Read your context and instructions
- Compiled the cybersecurity-prompt-guard-
I have completed the passive reconnaissance for example.com. No external API keys were used for this scan.
Domain Intelligence Report: example.com
Subdomain Discovery (via CT Logs)
| Subdomain | Source |
|---|---|
www.example.com | DigiCert |
dev.example.com | Let's Encrypt |
api.example.com | ZeroSSL |
SSL Certificate Inspection
| Field | Value |
|---|---|
| Issuer | DigiCert TLS RSA SHA256 2020 CA1 |
| Expiry Date | 2025-03-14 12:00:00 UTC |
| Days Remaining | 142 Days |
| Cipher Suite | TLS_AES_256_GCM_SHA384 |
| SANs | example.com, www.example.com |
DNS Records
A 93.184.216.34
AAAA 2606:2800:220:1:248:1893:25c8:1946
MX 0 .
TXT "v=spf1 -all"
Next steps
- Run
python scripts/domain_intel.py whois example.comto check registrar data. - Cross-reference identified subdomains against the Sherlock username database if specific handles are associated with this domain.
- Initiate a Web Pentest scan on
dev.example.comto check for misconfigured headers.
Connects securely to your tools. The creator never sees your data.
About this skill
Modern security teams struggle with fragmented tools and high-latency incident response. This package provides a 28-skill offensive and defensive toolkit for SecOps, OSINT, and cloud security automation.
What it does
- Google SecOps Orchestration manages the entire lifecycle of detection engineering, hunting, and triage within the Google Security Operations ecosystem.
- Offensive Security Testing executes authorized web penetration tests, smart contract audits, and bypasses LLM safety filters via G0DM0D3 and OBLITERATUS.
- Cloud Governance automates IAM policy simulation, privileged access management (PAM), and Security Command Center (SCC) remediation on Google Cloud.
- Passive OSINT performs reconnaissance on domains, usernames, and public records using tools like Sherlock and custom Python intelligence scripts.
- Supply Chain Forensics investigates open-source attacks on GitHub using a multi-agent framework for IOC extraction and evidence-backed reporting.
How it works
- Initialize by defining the engagement scope, such as a target domain, a Google Cloud project ID, or a GitHub repository.
- Select Mode based on the task, choosing between automated OSINT, interactive IAM troubleshooting, or evidence-first forensic investigation.
- Analyze & Simulate to identify vulnerabilities or evaluate detection coverage without mutating infrastructure.
- Remediate by generating structured plans and executing authorized CLI commands once user consent is confirmed.
Frameworks & tools
Google Cloud Platform (IAM, SCC, SecOps SOAR), YARA-L 2.0, Solidity, Python stdlib, Sherlock, and mechanistic interpretability tools for LLM weight analysis.
Why this beats prompting it yourself
Generic prompts fail to handle the strict state management required for forensics or the safety gates needed for cloud remediation. This skill enforces evidence-based reporting and prevents "hallucinated" security findings by requiring reproducible proof for every exploit and citation.
Use cases
- Audit Solidity smart contracts for economic and security vulnerabilities before deployment.
- Proactively hunt for undetected threats in Google SecOps using UDM event correlation.
- Automate the removal of personal data from 400+ data-broker sites.
- Perform supply-chain forensics on suspicious GitHub commits to identify IOCs.
Known limitations
Requires specific Google Cloud permissions (e.g., roles/policysimulator.admin) for cloud skills. OBLITERATUS is restricted to open-weight models for weight-level modifications.
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.
Requires GCP IAM roles for cloud tasks. Some OSINT tools need local CLI installation. LLM jailbreaking performance varies by model API updates.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 4 days ago
- Accounts
GitHub
Crt
Dns
Courtlistener
Gdeltproject
Icij
Cityofnewyork
Nyc
Treasury
Opencorporates
Sec
Senate
Usaspending
Archive
Wikidata
Ca
Vermont
Oregon
Appianportalsgov
Target
- Software
Python@google/mcp-developer-knowledge-server
Node.jsPolicy Troubleshooter MCPUse Policy Troubleshooter MCPrea-agentsGoogle SecOps MCP
Git
Permissions
Allowed Hosts