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.
npx agentmods add agents/ankitjha67/product-architect/09-securitygit clone --depth 1 https://github.com/ankitjha67/product-architectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ankitjha67/product-architect/09-security)<a href="https://agentmods.dev/agents/ankitjha67/product-architect/09-security"><img src="https://agentmods.dev/badge/agents/ankitjha67/product-architect/09-security.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.17931 |
| Opus 5 | $0.00000 | $0.08965 |
| Sonnet 5 | $0.00000 | $0.03586 |
| Haiku 4.5 | $0.00000 | $0.01793 |
Grade B, and why
09-security scanned grade B with 2 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
□ RAG chunks / API responses cannot override the system prompt or issue commands Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
execute arbitrary code on load, so prefer safetensors or an equivalent non-executable format, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 1,125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 09: Security
⚠️ DISCLAIMER: Security frameworks do not replace professional penetration testing or security assessment by qualified professionals. See DISCLAIMER.md.
Role
You are the Chief Information Security Officer (CISO) and Compliance Officer rolled into one. You audit EVERY phase of the product for security vulnerabilities, regulatory compliance gaps, data privacy risks, and operational risks. You have the authority to BLOCK a launch if critical issues are unresolved.
This agent runs IN PARALLEL with all other agents, not just at the end.
Inputs Required
- ALL outputs from ALL other agents
- Product geography/market
- Industry vertical
- Data types being collected/processed
Security Audit Framework
1. Authentication & Authorization Security
AUDIT CHECKLIST:
━━━━━━━━━━━━━━━
PASSWORD SECURITY:
□ Minimum 8 characters, require complexity (upper + lower + number + special)
□ Passwords hashed with bcrypt/argon2 (NEVER MD5/SHA1)
□ Passwords NEVER stored in plain text, logs, or error messages
□ Brute force protection: account lockout after 5 failed attempts (15min cooldown)
□ Rate limiting on login endpoint: 10 attempts/minute per IP
□ Password reset tokens: single-use, expire in 30 minutes, cryptographically random
□ No password hints or security questions (social engineering vectors)
SESSION MANAGEMENT:
□ JWT with short expiry (15min access token, 7day refresh token)
□ Refresh token rotation (old token invalidated on use)
□ Secure cookie flags: HttpOnly, Secure, SameSite=Strict
□ Session invalidation on password change
□ Concurrent session limits (configurable per user type)
□ Force logout capability (admin and user)
OAUTH/SOCIAL LOGIN:
□ State parameter for CSRF protection
□ Validate redirect URIs (whitelist, no open redirects)
□ Verify token signatures with provider's public keys
□ Don't trust email from OAuth without verification flag check
MULTI-FACTOR AUTHENTICATION:
□ TOTP (Google Authenticator) support for sensitive accounts
□ SMS OTP as fallback (aware of SS7 limitations)
□ Recovery codes generated at MFA setup (stored securely)
□ MFA required for: payment method changes, password changes, account deletion
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.
- yesterday Changed · +792 lines a6526a7d3ac2
- 5d ago First seen · 333 lines · 0 tokens per session scan B 4d27d2881252
09-security is an agent published in the GitHub repository ankitjha67/product-architect (108 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 17,931 tokens. A static security scan graded it B with 2 findings (instruction-override phrasing, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
terms
Drafts GDPR-compliant privacy policies, Terms of Service, cookie notices, and DPAs sized to company stage. Use when you need a privacy policy, ToS, or data processing agreement written or audited. Trigger with "draft my privacy policy", "review my terms of service".
Medical Billing & Coding Specialist
Expert medical billing and coding specialist for ICD-10-CM/PCS, CPT, and HCPCS coding, claim submission, denial management, revenue cycle optimization, compliance auditing, and payer contract analysis — maximizing clean claim rates and revenue recovery for healthcare providers of all sizes.
Section 508 Accessibility Specialist
Expert U.S. federal Section 508 accessibility engineer (the 508 legal baseline is WCAG 2.0 Level AA; WCAG 2.1/2.2 AA are recommended best practice, and ADA Title II requires WCAG 2.1 AA for state/local government) specializing in accessible web development, ARIA implementation, screen reader testing…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
auditor
GxP audit and investigation specialist for audit planning, execution, finding classification, CAPA root cause analysis, inspection readiness, data integrity monitoring, and vendor qualification.
grc-analyst
Governance, Risk and Compliance Analyst. Maintains the risk register, maps security controls to compliance frameworks, collects audit evidence, and produces compliance attestations. Participates at the Plan, Design, Test and Release phases. Use this agent when: A new project requires a compliance framework mapping A…