Security for AI-native developers
Superagent is the author of a set of security skills that help AI agents audit other agent skills before installation, review GitHub repositories and GitHub Actions workflows for hardening gaps, and check new dependencies for supply-chain compromise such as malicious install scripts and credential-harvesting worms. Their skills also cover triaging vulnerability reports and advisories to separate real, disclosable issues from noise, and running scoped offensive engagements and red-team loops against LLM guardrails. What stands out is the focus on security work for AI-native development, where agents themselves handle skills, pipelines and dependencies.
Skills
14 skills · 80 stars · MIT
Authz Security Review application source code for broken authorization — IDOR / Broken Object Level Authorizatio…
Ci Cd Security Scan GitHub Actions workflow files for security vulnerabilities by reading the YAML and reporting…
Crypto Secrets Audit application source code and configuration for cryptography and secrets hygiene issues: hard…
Hacker Cursor-native offensive security engagement and exploitability autoresearch orchestrator inspired…
Infra Security Audit Infrastructure-as-Code for security misconfigurations before it ships — Terraform (.tf/.tfv…
Pr Github Ops Post Superagent PR security scan findings as inline GitHub pull request review comments using the…
Recon Security Guide authorized external penetration testing from recon through validation and scoped exploitati…
Redteam Autoresearch Run a bounded red-teaming autoresearch loop to generate LLM guardrail training data.
Repo Security Posture Audit a GitHub repository's security posture and hardening gaps across branch protection, CODEOWN…
Security Disclosure Triage Verify whether an incoming security advisory is a real, disclosable vulnerability in a target rep…
Skill Security Audit an AI agent skill for security risks before installing or trusting it.
Superagent Set up Superagent Context Guardrails at coding-agent tool boundaries, configure and safely use th…
Supply Chain Security Review new or changed dependencies for supply-chain compromise before they enter a project — mali…
Vulnerability Triage Triage inbound vulnerability reports - GitHub Advisories (GHSA/CVE), bug bounty submissions, Hack…