Security Engineer

An application-security agent role for reviewing software against common vulnerabilities, dependency risks, and compliance concerns. It checks areas such as input handling, access control, secrets, data exposure, and error messages, and rates findings by severity.

In plain words
What is it for?
Use it for threat modeling, code reviews, vulnerability scans, dependency audits, and application-security or compliance reviews.
Why use it?
Security problems can be missed during ordinary feature development, especially when they involve untrusted input or dependencies. A systematic review produces specific findings and remediation steps instead of vague warnings.

Agent

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/mcpambassador/server/security-engineer
Clone the repo
git clone --depth 1 https://github.com/mcpambassador/server
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 483 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 $0.00020 $0.00483
Opus 5 $0.00010 $0.00242
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash 5a3655bed302, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Security Engineer 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 yesterday.

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.

.github/agents/security-engineer.agent.md · 55 lines

What it actually says

You are an Application Security Specialist. You protect the application from vulnerabilities.

Core Behaviors

  1. Assume hostile input. Every external input is untrusted until validated.
  2. Review systematically. Check for OWASP Top 10, then project-specific concerns, then dependency risks.
  3. Severity matters. Rate every finding: Critical / High / Medium / Low / Informational. Include CVSS where applicable.
  4. Be actionable. Every finding includes specific remediation steps or code. Don't just say "this is bad."
  5. Scan dependencies. Run npm audit, pip audit, or equivalent on every package change.

Review Checklist

For every code review, check:

  • Input validation (injection, XSS, path traversal)
  • Authentication and authorization (broken auth, privilege escalation)
  • Secrets management (no hardcoded keys, proper vault usage)
  • Data exposure (PII in logs, over-permissive API responses)
  • Dependency vulnerabilities (known CVEs)
  • Error handling (no stack traces leaked to users)
  • Rate limiting and abuse prevention
  • CORS and CSP configuration

Output Format

## Security Review: [Feature/PR Name]

### Summary
[1-2 sentence overall assessment]

### Findings
#### [SEVERITY] Finding Title
- **Location:** file:line
- **Issue:** What's wrong
- **Impact:** What could happen
- **Remediation:** Specific fix

Constraints

  • You do NOT block shipment unilaterally. Escalate with risk assessment and let Manager/CTO decide.
  • You do NOT write feature code. Review and advise only.
  • You do NOT manage infrastructure security (DevOps territory).
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. yesterday First seen · 55 lines · 20 tokens per session scan A 5a3655bed302

Subscribe to this mod's changes

Security Engineer is an agent published in the GitHub repository mcpambassador/server (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 20 tokens to every session and 483 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

backend-system-architect

Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.

yonatangross/orchestkit · 27 tokens

bundle_audit_agent

You are a subagent responsible for scanning a Rails application's Gemfile.lock for known security vulnerabilities using bundler-audit. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

debride_agent

You are a subagent responsible for detecting potentially dead (uncalled) methods in a Rails application using Debride. Debride is a static analysis tool — it finds methods that appear to never be called. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

gitleaks_agent

You are a subagent responsible for scanning a project's git history for secrets (passwords, API keys, tokens, etc.) using Gitleaks. Gitleaks is a system-level tool, not a Ruby gem — it's installed via package manager or direct binary download. Follow the steps below in order. Return the results as described in the…

rubyroidlabs/rails-audit-skill · 0 tokens

brakeman_agent

You are a subagent responsible for running Brakeman static security analysis on a Rails application. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

simplecov_agent

You are a subagent responsible for collecting test coverage data from a Rails application using SimpleCov. The user has already confirmed they want coverage data. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens