Does it replace static code analysis (SAST)?

No, this skill is designed for real-time threat recognition and behavioral security. You should still use dedicated SAST tools for scanning source code for vulnerabilities.

When should I enable this skill?

Enable this skill whenever your agent handles email, navigates untrusted URLs, manages API keys, or interacts with sensitive credential vaults.

Why does it analyze URLs right-to-left?

Analyzing from right-to-left helps identify the actual registrable domain, preventing attackers from using deceptive subdomains to mimic legitimate services.

How does this skill detect phishing?

It analyzes sender domains character-by-character and evaluates communication for social engineering tactics like artificial urgency, authority pressure, and unexpected banking detail changes.

Can it prevent API key leaks?

Yes, the skill mandates that the agent inspects all content for embedded secrets—such as tokens, passwords, and connection strings—before sharing or forwarding data.

Security Awareness Expert

Name: Security Awareness Expert
Author: trailofbits

bytrailofbits

•

277

•

Security & Testing

Protects users and systems by identifying phishing attempts, verifying domains, and preventing credential leaks before actions are taken.

The Security Awareness skill transforms Claude into a vigilant cybersecurity analyst capable of recognizing and neutralizing common attack vectors like phishing, social engineering, and credential harvesting. It provides a defensive layer for agents interacting with emails, URLs, or sensitive data stores by enforcing rigorous domain verification and content inspection before any navigation or data sharing occurs. Developed with best practices for threat detection, this skill ensures that autonomous agents remain secure even when handling untrusted data or communicating in sensitive environments.

Key Features

01Automated identification and flagging of embedded secrets and API keys

02Proactive phishing and Business Email Compromise (BEC) detection

03Right-to-left domain verification for URL and email safety

04Detection of social engineering signals like urgency and authority pressure

05Enforcement of secure channels for sensitive data and credential handling

06277 GitHub stars

Use Cases

01Triaging incoming emails to filter out malicious links and credential harvesting attempts

02Scanning documentation or logs to prevent the accidental exposure of tokens in public trackers

03Verifying third-party URLs before allowing an agent to navigate or interact with web content

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add trailofbits/skills-curated security-awareness

For use in Claude.ai and ChatGPT

Download Skill