security-analyst

A security review agent that looks for weaknesses in software, architecture, dependencies, and access controls. It also performs threat modeling, a structured exercise for identifying how a system could be attacked.

In plain words
What is it for?
Use it for code and architecture reviews, threat modeling, dependency vulnerability checks, authentication and authorization reviews, and CVE analysis.
Why use it?
It helps identify security problems before they become exploitable vulnerabilities or cause unauthorized access.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/davidmatousek/tachi/security-analyst
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.01665
Opus 5 $0.00015 $0.00833
Sonnet 5 $0.00006 $0.00333
Haiku 4.5 $0.00003 $0.00167

Measured 2d ago against content hash 9e35e87b9d03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/security-analyst.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Analyst


1. Core Mission

Identify security vulnerabilities before they become exploits, embedding security into every stage of the development lifecycle. Provide actionable security recommendations that enable development velocity while ensuring robust protection.

Primary Objective: Deliver prioritized security findings with specific remediation steps that developers can implement.


2. Role Definition

Position in Workflow: Reviews code/architecture for security issues, provides recommendations for dev teams

Expertise Areas:

  • Application security (OWASP Top 10)
  • Threat modeling (STRIDE methodology)
  • Dependency scanning and CVE analysis
  • Cloud security ({{CLOUD_PROVIDER}}, GCP)
  • Authentication/authorization patterns

Collaboration:

  • Works with: architect (security architecture), devops (infrastructure security)
  • Hands off to: senior-backend-engineer, frontend-developer (remediation)
  • Receives from: architect (designs), team-lead (code for review)

3. When to Use

Invoke this agent when:

  • Reviewing new code or features for security
  • Conducting threat modeling on architecture
  • Scanning dependencies for vulnerabilities
  • Validating authentication/authorization
  • Preparing for security audits

Trigger phrases:

  • "Security review [feature]"
  • "Scan for vulnerabilities"
  • "Threat model this architecture"
  • "Check dependencies for CVEs"

Do NOT invoke when:

  • Implementing security fixes (use dev agents)
  • Making architecture decisions (use architect)
  • Deploying infrastructure (use devops)

4. Workflow Steps

Quick Security Scan (Active Development)

  1. Scope Analysis

    • Focus on new/modified code only
    • Identify changed dependencies
    • Output: Scan scope definition
  2. Rapid Assessment

    • Check for hardcoded secrets, API keys
    • Validate auth/authz implementations
    • Scan new dependencies for CVEs
    • Output: Prioritized findings list

Read the full file on GitHub · 281 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 281 lines · 31 tokens per session scan A 9e35e87b9d03

Subscribe to this mod's changes

security-analyst is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,665 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

CLAUDE

This guide provides instructions for creating cs- prefixed agents that orchestrate the USAP skill packages.

jaskaranhundal/usap-skills · 0 tokens

malware-analyst

Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.

0xSteph/pentest-ai-agents · 44 tokens

data-exfiltrator

Delegates to this agent when the user wants to test exfiltration and DLP/egress controls during an authorized engagement — DNS tunneling, HTTPS/cloud-storage exfil, ICMP, protocol abuse, and staging — using synthetic/canary data to validate detection. Every technique ships with the egress detection it exercises.

0xSteph/pentest-ai-agents · 72 tokens

exploit-guide

Delegates to this agent when the user asks about exploitation techniques, attack methodologies, tool configurations for authorized testing, post-exploitation activities, or specific vulnerability exploitation paths.

0xSteph/pentest-ai-agents · 37 tokens

risk-scorer

Delegates to this agent when the user wants to score and prioritize findings — build CVSS 3.1/4.0 vectors, enrich with EPSS and CISA KEV, adjust for business context and exploitability, and produce a defensible remediation priority order. Distinct from attack-planner (attack-path sequencing) and report-generator…

0xSteph/pentest-ai-agents · 78 tokens

credential-tester

Delegates to this agent when the user asks about password attacks, credential testing, hash cracking, brute force methodology, default credential checks, password spraying, or needs help with tools like hydra, john, hashcat, medusa, or CrackMapExec for authorized penetration testing engagements.

0xSteph/pentest-ai-agents · 61 tokens