Home › Agent skills › Shannon: Autonomous AI Pentester
Security & Compliance

Shannon: Autonomous AI Pentester skill

An AI pentester for web applications and APIs. It analyses your source code, identifies attack vectors and executes real exploits, with OWASP-focused coverage of injection, XSS, SSRF and broken authentication and authorization. A black-box mode tests a running application without source code.

Run it in AGNT — freeView on GitHub

Why it matters

It reports what it could actually exploit rather than what might be wrong. It executes real attacks, so run it only against applications you own or are authorised to test, and never against production. Shannon is a full tool rather than a single SKILL.md.

How to install Shannon: Autonomous AI Pentester

  1. From the repository. Shannon: Autonomous AI Pentester ships as a full tool rather than a single SKILL.md folder. Follow the setup in its README.
  2. In AGNT. Download AGNT free, then add the skill folder from Skills → Import. It runs with the model you choose, next to your agents, workflows and memory.

Source and maintenance

RepositoryKeygraphHQ/shannon
GitHub stars (13 November 2026)51,825
Last commit11 Nov 2026
CategorySecurity & Compliance
Ranked#48 in The 100 Best AI Agent Skills in 2027

Checked against GitHub on 13 November 2026.

The AGNT briefing

Stay in the loop.

New agents, workflows and field notes. Sign up for AGNT updates.

By subscribing, you agree to receive AGNT updates. Unsubscribe any time. Privacy policy.