security-check

A detailed checklist for reviewing security-sensitive code changes. It treats all external input as potentially controlled by an attacker and checks where that input crosses into trusted operations.

In plain words
What is it for?
Reviewing changes involving authentication, encryption, payments, input handling, dependencies, build pipelines, infrastructure, or database migrations.
Why use it?
It helps find concrete vulnerabilities instead of offering general security advice. The review covers missing permission checks, exposed secrets, unsafe parsing, injection, unbounded input, and unsafe file or URL handling.

Skill for Claude CodeCodex

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 skills/lingoverse/mimir/security-check
Any agent
npx skills add LingoVerse/mimir --skill security-check
Clone the repo
git clone --depth 1 https://github.com/LingoVerse/mimir

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 686 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 $0.00048 $0.00686
Opus 5 $0.00024 $0.00343
Sonnet 5 $0.00010 $0.00137
Haiku 4.5 $0.00005 $0.00069

Measured 2d ago against content hash f9bd668d16ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-check 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 2d 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/skills/security-check/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Check

This pass runs only when the diff touches a security-sensitive surface. Assume an adversary controls every input. Your job is to find the specific line where a trust boundary is crossed without a check — not to give a generic security lecture.

Trust-boundary checklist

Walk the changed code and ask, for each external input:

  • Injection — Is user-controlled data concatenated into SQL, shell commands, HTML, templates, regex, or file paths without parameterization/escaping? Flag the exact line.
  • AuthN / AuthZ — Does a new endpoint, route, or handler verify identity AND permissions? Look for missing ownership checks (IDOR: can user A act on user B's resource by changing an ID?).
  • Secrets — Any API key, token, password, private key, or connection string hardcoded or logged? Any secret added to a non-secret config file?
  • Input validation — Are size, type, range, and format validated before use? Unbounded input → DoS. Unvalidated redirects/URLs → SSRF / open redirect.
  • Deserialization & parsing — Untrusted data into eval, Function, YAML/pickle loaders, or XML parsers with external entities?
  • Path traversal — User input in file paths without normalization + allowlist?
  • Crypto — Home-rolled crypto, weak/legacy algorithms, missing randomness, predictable tokens, comparison of secrets with non-constant-time equality?
  • Dependencies — New dependency added: is it reputable and pinned? Manifest change that widens version ranges or pulls an unmaintained package?
  • CI / IaC / Docker — New workflow running untrusted PR code with secrets in scope? pull_request_target misuse? Overly broad cloud IAM? Container running as root, secrets baked into image layers?
  • Migrations — Destructive or non-reversible schema change? Data exposure via a new column/table without access control?

Reporting

Use the same JSON output format as review-rubric. For each security finding:

  • Severity is almost always critical or major. Reserve critical for exploitable issues (clear path from attacker input to impact) and confirmed secret exposure.
  • In body, state the attack: "An attacker who controls X can do Y because Z is not checked." Concrete, not theoretical.
  • In suggestion, give the specific mitigation (parameterized query, authz check location, validation, constant-time compare), not "sanitize the input".

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 48 tokens per session scan A f9bd668d16ab

Subscribe to this mod's changes

security-check is a skill published in the GitHub repository LingoVerse/mimir (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 686 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

testing-skill

Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.

pydantic/pydantic-ai · 44 tokens

google-drive-sheets

Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.

yc-software/qm · 31 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

slack-drafts

Create Slack message drafts in the user's own composer, as the user, through their per-user Slack OAuth. Drafting only — the user reviews and sends from Slack.

yc-software/qm · 38 tokens