context-dev-api-security

Rules for securely authenticating and handling side effects in Context.dev integrations. Side effects are actions that change data or affect an outside service.

In plain words
What is it for?
Use them when building or reviewing Context.dev integrations, especially code that runs in a browser or performs account-changing actions.
Why use it?
They help prevent exposed credentials, unsafe browser requests, and unintended submissions, overwrites, cancellations, or deletions.

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/context-dot-dev/cursor-plugin/context-dev-api-security
Clone the repo
git clone --depth 1 https://github.com/context-dot-dev/cursor-plugin
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 210 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 $0.00012 $0.00210
Opus 5 $0.00006 $0.00105
Sonnet 5 $0.00002 $0.00042
Haiku 4.5 $0.00001 $0.00021

Measured yesterday against content hash 2880e0c53226, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-dev-api-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 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.

rules/context-dev-api-security.mdc · 13 lines

What it actually says

context-dev-api-security:

  • Use Cursor OAuth for the bundled context MCP server. Never ask users to paste an MCP credential into chat.
  • When application code calls the REST API or SDK directly, never expose CONTEXT_DEV_API_KEY in browser bundles, client-side environment variables, logs, or committed files. Read it server-side and proxy browser requests through a backend.
  • For high-volume logo rendering in UI, use Logo Link (https://logos.context.dev/?publicClientId=...&domain=...) with a public client ID instead of calling the brand API from the frontend.
  • Handle 422 responses from email-based endpoints as "skip enrichment" for free or disposable email providers.
  • Treat browser actions, monitor changes, and batch lifecycle operations according to their real side effects. Require explicit user intent before an operation can submit forms, trigger webhooks, overwrite monitor configuration, cancel work, or delete stored data.
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 · 13 lines · 12 tokens per session scan A 2880e0c53226

Subscribe to this mod's changes

context-dev-api-security is a cursor rule published in the GitHub repository context-dot-dev/cursor-plugin (4 stars, last pushed 14d ago), licensed MIT. It adds 12 tokens to every session and 210 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.