AI Pentesting

Use AI agents to autonomously conduct penetration tests on web applications. Combine LLM reasoning with security tools (nmap, subfinder, nuclei, sqlmap, browser automation) to find and prove vulnerabilities with minimal human intervention.

Overview

The AI Pentesting skill, hosted within the TerminalSkills/skills repository, enables autonomous security assessments of web applications. By integrating large language model reasoning with industry-standard security utilities, this skill allows agents like Claude, Gemini, and Codex to perform complex vulnerability discovery. The system utilizes tools such as nmap for network scanning, subfinder for subdomain discovery, and nuclei for template-based scanning. It further incorporates sqlmap and browser automation to identify and validate security flaws with minimal human oversight. This implementation, part of a project with 71 stars on GitHub, provides a structured approach for AI agents to conduct end-to-end security reviews, leveraging Python-based automation to bridge the gap between LLM intelligence and practical security tooling.

Use Cases

Automated discovery of subdomains and open ports on target web applications.
Identification and proof-of-concept validation for SQL injection vulnerabilities.
End-to-end security scanning using browser automation to simulate user interactions.

Install Notes

# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/ai-pentesting/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

This skill executes active security scanning tools and browser automation, which may trigger defensive alerts or impact target system stability. Users should ensure they have explicit authorization before deploying these autonomous agents against any infrastructure, as the LLM-driven reasoning process may perform unpredictable sequences of security tests.

Related Skills

Skill Improver

trailofbits/skills

Security

Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a skill. Triggers on 'fix my skill', 'improve sk

Claude CodeClaude
securityreview
5,853 starsSource linked

Sarif Parsing

trailofbits/skills

Security

Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT r

Claude CodeClaude
pythonsecurity
5,853 starsSource linked

Semgrep

trailofbits/skills

Security

Run Semgrep static analysis scan on a codebase using parallel subagents. Supports two scan modes — "run all" (full ruleset coverage) and "important only" (high-confidence security vulnerabilities). Automatically detects and uses Semgrep Pro for cross-file taint analysis when available. Use when asked to scan code for v

Claude CodeClaude
pythonsecurity
5,853 starsSource linked

Supply Chain Risk Auditor

trailofbits/skills

Security

Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements.

Claude CodeClaude
securityresearch
5,853 starsSource linked

Cargo Fuzz

trailofbits/skills

Security

cargo-fuzz is the de facto fuzzing tool for Rust projects using Cargo. Use for fuzzing Rust code with libFuzzer backend.

Claude CodeClaude
securityresearch
5,853 starsSource linked

Fuzzing Obstacles

trailofbits/skills

Security

Techniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer progress.

Claude CodeClaude
securitytesting
5,853 starsSource linked