security

A command that audits application programming interfaces, or APIs, against the OWASP API Top 10 security risks.

In plain words
What is it for?
Use it to review local OpenAPI or Swagger specifications and, when connected, Postman collections for security problems and remediation guidance.
Why use it?
It helps find common API weaknesses such as missing authentication, exposed sensitive data, insecure connections, and weak input checks.

Command

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 commands/postman-devrel/postman-claude-code-plugin/security
Clone the repo
git clone --depth 1 https://github.com/Postman-Devrel/postman-claude-code-plugin
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,188 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 $0.00019 $0.01188
Opus 5 $0.00010 $0.00594
Sonnet 5 $0.00004 $0.00238
Haiku 4.5 $0.00002 $0.00119

Measured yesterday against content hash e0dd5439278c, 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 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.

commands/security.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Security Audit

Audit your API for security issues: missing auth, exposed sensitive data, insecure transport, weak validation, and OWASP API Security Top 10 alignment. Works with local OpenAPI specs and Postman collections.

Prerequisites

For collection auditing, the Postman MCP Server must be connected. Local spec auditing works without MCP. If needed, tell the user: "Run /postman:setup to configure the Postman MCP Server."

Workflow

Step 1: Find the Source

Call getWorkspaces to get the user's workspace ID. If multiple workspaces exist, ask which to use.

Local spec:

  • Search for **/openapi.{json,yaml,yml}, **/swagger.{json,yaml,yml}

Postman spec (via MCP):

  • Call getAllSpecs with the workspace ID to find specs
  • Call getSpecDefinition for the full spec content

Postman collection (via MCP):

  • Call getCollections with the workspace parameter
  • Call getCollection for full detail including auth config
  • Call getEnvironment to check for exposed secrets

Step 2: Run Security Checks

Authentication and Authorization:

  • Security schemes defined (OAuth2, API Key, Bearer, etc.)
  • Security applied globally or per-endpoint
  • No endpoints accidentally unprotected
  • OAuth2 scopes defined and appropriate
  • Admin endpoints have elevated auth requirements

Transport Security:

  • All server URLs use HTTPS
  • No mixed HTTP/HTTPS

Sensitive Data Exposure:

  • No API keys, tokens, or passwords in example values
  • No secrets in query parameters (should be headers/body)
  • Password fields marked as format: password
  • PII fields identified
  • Postman environment variables checked for leaked secrets (via getEnvironment)

Input Validation:

  • All parameters have defined types
  • String parameters have maxLength
  • Numeric parameters have minimum/maximum
  • Array parameters have maxItems
  • Enum values used where applicable
  • Request body has required field validation

Rate Limiting:

  • Rate limits documented
  • Rate limit headers defined (X-RateLimit-Limit, X-RateLimit-Remaining)
  • 429 Too Many Requests response defined

Read the full file on GitHub · 130 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. yesterday First seen · 130 lines · 19 tokens per session scan A e0dd5439278c

Subscribe to this mod's changes

security is a command published in the GitHub repository Postman-Devrel/postman-claude-code-plugin (38 stars, last pushed 27d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,188 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 2026-08-30.

Related

Other commands, from other repositories