owasp-ai-security-privacy

owasp-ai-security-privacy is a cursor rule for Cursor from adonai-labs/agent-runway. It costs 515 tokens per session, scanned A, original, MIT.

A set of pull-request rules based on OWASP guidance for protecting data and keeping AI systems safe. OWASP is an organisation that publishes widely used application-security guidance.

In plain words
What is it for?
Use it when reviewing AI-related code that handles personal or health data, prompts, outputs, credentials, external tools, or other sensitive information.
Why use it?
It helps teams spot privacy, access-control, secret-handling, monitoring, and misuse risks before code is merged.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when reviewing AI-related code that handles personal or health data, prompts, outputs, credentials, external tools, or other sensitive information.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/adonai-labs/agent-runway/owasp-ai-security-privacy
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.

Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway

Made for: Cursor.

Wrote 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.

agentmods badge for owasp-ai-security-privacy

README.md
[![agentmods](https://agentmods.dev/badge/rules/adonai-labs/agent-runway/owasp-ai-security-privacy/github.svg)](https://agentmods.dev/rules/adonai-labs/agent-runway/owasp-ai-security-privacy)
Your own site
<a href="https://agentmods.dev/rules/adonai-labs/agent-runway/owasp-ai-security-privacy"><img src="https://agentmods.dev/badge/rules/adonai-labs/agent-runway/owasp-ai-security-privacy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for owasp-ai-security-privacy

Your own site · 80×15
<a href="https://agentmods.dev/rules/adonai-labs/agent-runway/owasp-ai-security-privacy"><img src="https://agentmods.dev/badge/rules/adonai-labs/agent-runway/owasp-ai-security-privacy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 515 This file is loaded in full into every session.
When invoked 515 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00515 $0.00515
Opus 5 $0.00258 $0.00258
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 10d ago against content hash e24596877ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

owasp-ai-security-privacy 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 10d 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/owasp-ai-security-privacy.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OWASP AI Security & Privacy – PR Review Rules

Data Governance

  • Classify inputs/outputs; prohibit uncontrolled ingestion of sensitive categories (PII, PHI, credentials).
  • Minimize retention; delete intermediates; avoid storing raw prompts/outputs unless justified.
  • Document data sources and consent; prefer data references over raw payloads.

Privacy by Design

  • Redact data before prompts; support field-level masking and hashing.
  • Provide opt-out and data deletion pathways where applicable.
  • Disable training/fine-tuning on user data by default in production.

Access Control and Secrets

  • Secrets in secure variables/key vault; rotate regularly; scope by environment.
  • Principle of least privilege for service principals and tokens used by tools.

Monitoring & Incident Response

  • Capture minimal operational telemetry (latency, tokens, errors) without sensitive content.
  • Threshold alerts for spikes, cost anomalies, and failure patterns.
  • Provide runbooks for key incident types (leak, poisoning, abuse, drift).

Safety & Abuse Prevention

  • Add content/abuse filters for inputs/outputs appropriate to domain.
  • Restrict high-risk actions (code exec, network, file writes) behind approvals.
  • Sandbox tool execution; apply egress allowlists and filesystem quotas.

Model & Supply Chain Risk

  • Track model/SDK versions; maintain SBOM; verify signatures/hashes when available.
  • Evaluate model updates in a staging environment; document behavior changes.

Compliance & Auditability

  • Log decision rationale for automated actions (without sensitive content).
  • Keep configuration-as-code for prompts, tools, and safety policies.

PR Reviewer Checklist

  • Sensitive data is redacted/masked; no raw secrets in code or logs.
  • No long-term storage of prompts/outputs without a clear purpose.
  • Access tokens scoped and stored securely; least privilege enforced.
  • Telemetry avoids sensitive content; alerts configured for anomalies.
  • Risky capabilities gated; sandboxing and allowlists in place.
  • Dependencies/models pinned; update process documented.
  • Policies and prompts are versioned and reviewable.

Read the full file on GitHub · 52 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. 10d ago First seen · 52 lines · 515 tokens per session scan A e24596877ddd

Subscribe to this mod's changes

owasp-ai-security-privacy is a cursor rule published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 20d ago), licensed MIT. It adds 515 tokens to every session, about $0.0026 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.