Application Security Auditor — Security agent for Claude Code
Local-only, static-first application-security auditor that threat-models a repository or subsystem and returns validated source-to-sink findings without external access or fixes.
How to install Application Security Auditor
Installs to ~/.claude/agents/latent-sre-sde-agents-application-security-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/latent-sre/sde-agents/HEAD/agents/application-security-auditor.md -o ~/.claude/agents/latent-sre-sde-agents-application-security-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Application Security Auditor does
name: application-security-auditor description: Local-only, static-first application-security auditor that threat-models a repository or subsystem and returns validated source-to-sink findings without external access or fixes. Use for "security audit this repository", "threat model X", "how could this code be attacked", or local reachability of a supplied advisory. Not for a PR/branch diff (use sde-agents:code-reviewer), external CVE or vendor research (use sde-agents:researcher), ordinary l
Alternatives in Security
- Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
- Fleet Security Auditor — Fleet-specific security analysis covering MDM, osquery, API auth, and device management threat models 6.8k ★
- JS Analyzer — JavaScript static analysis agent for client-side security review 812 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Deep Repo Auditor
Cross-validated deep repository audit — dual AI models (Sonnet + Codex) in parallel, consolidated report with
Docs Fixer
Applies validated fixes from docs-checker audit reports. Re-validates factual accuracy findings before applyin
Docs Software Engineering Separation Fixer
Applies validated fixes from docs-software-engineering-separation-checker audit reports. Fixes missing prerequ
Phase2 API Designer
Designs the API layer of a tech spec: RESTful contract-first design and integration patterns, building on data
Log Reviewer
Audit roku-log usage in a JellyRock BS/BRS file or function. Defaults to AUDIT-ONLY: lists logging gaps withou
Be Auth
Authentication and authorization work — guards, tokens, SSO/external login handoffs, policies, and access pred
Related Skills
Threat Model Skill
Claude Code skill: write the project's security constitution (assets, roles, trust boundaries, invariants, ent
Subsystem
Scaffold a custom Alfresco subsystem (ChildApplicationContextFactory + default/instance properties) or, in aut
Openclaw Skill
ZettelForge v2.0.0 — CTI agentic memory system. Hybrid TypeDB (STIX 2.1) + LanceDB (vectors). Zero external AI