security

A collection of secure coding rules for software that handles user input, identities, passwords, secrets, or sensitive information. It includes guidance on validation, authentication, permissions, encryption, and database queries.

In plain words
What is it for?
Use it when writing or reviewing login flows, access checks, file uploads, URLs, password storage, tokens, and code that reads or writes sensitive data.
Why use it?
It helps prevent common security weaknesses, such as accepting unsafe input, storing passwords plainly, or building database queries from raw text.

Cursor rule

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 rules/adonai-labs/agent-runway/security
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,426 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 $0.00000 $0.01426
Opus 5 $0.00000 $0.00713
Sonnet 5 $0.00000 $0.00285
Haiku 4.5 $0.00000 $0.00143

Measured 3d ago against content hash 30d0aed22ae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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 3d 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.

src/core/rules/security.mdc · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Guidelines

Directives for secure coding. Apply when handling input, identity, secrets, or sensitive data.


Input Validation

  • Validate all caller-supplied data at the boundary — type, format, range, and length
  • Reject invalid input explicitly; do not sanitise and proceed
  • Use schema validation (e.g. Zod, FluentValidation) for structured input
  • Enforce length limits to prevent buffer overflow and DoS
  • Validate file uploads: type allowlist, size limits, and content inspection
  • Validate URLs before use: allowlist scheme and host; reject file://, localhost, internal IPs

Parameterised queries only:

-- Good: parameterised
SELECT * FROM users WHERE id = $1
-- Bad: string concatenation
SELECT * FROM users WHERE id = '${id}'

Authentication

  • Verify identity before checking permissions; never allow partial or anonymous access to sensitive operations
  • Hash passwords with bcrypt (salt rounds ≥ 12) or Argon2; never store plaintext
  • JWT: use short expiry (≤ 15 min for access tokens); validate issuer, audience, and expiry; use strong secret
  • Prefer refresh tokens for session extension; store securely (httpOnly, secure, SameSite)
  • Enable MFA for privileged or sensitive operations
  • Implement rate limiting on login and password-reset endpoints
  • Use constant-time comparison for tokens and secrets

Authorisation

  • Authorise at the resource level; verify the authenticated user may access the specific resource requested
  • Do not rely only on role checks; verify resource ownership in business logic
  • Default to deny; require explicit grant for elevated access
  • Missing authorisation on one endpoint is an access control failure
  • Implement RBAC with least privilege; map roles to permissions explicitly

Data Protection

  • Encrypt sensitive data at rest (AES-256-GCM) and in transit (TLS 1.2+)
  • Use platform-provided crypto; never implement custom algorithms
  • Never use MD5 or SHA-1 for security purposes; use SHA-256 or higher
  • Store keys in a secrets manager; inject at runtime; rotate on compromise
  • Enforce HSTS for web applications
  • Use secure defaults: restrict CORS, disable debug in production

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 0 tokens per session scan A 30d0aed22ae9

Subscribe to this mod's changes

security is a cursor rule published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,426 tokens. 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.