security-reviewer

security-reviewer is an agent for Claude Code from Sassy-Dog/sassydog-skills. It costs 57 tokens per session (1,572 once invoked), scanned A, original, Apache-2.0.

A security audit specialist for applications, software dependencies, automated pipelines, and operational systems.

In plain words
What is it for?
Reviewing authentication, secrets, input handling, third-party packages, CI systems, infrastructure settings, logs, and data exposure, with evidence and remediation guidance.
Why use it?
It finds realistic risks such as stolen credentials, injection attacks, weak access controls, and unsafe dependencies before they can cause harm.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sassy-dog plugin — 21 skills, 10 agents shipped together

Good fit Reviewing authentication, secrets, input handling, third-party packages, CI systems, infrastructure settings, logs, and data exposure, with evidence and remediation guidance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sassy-dog/sassydog-skills/security-reviewer
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/Sassy-Dog/sassydog-skills

Made for: Claude Code.

Or install sassy-dog, the plugin that ships this one along with the rest of its 21 skills, 10 agents.

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sassy-dog/sassydog-skills/security-reviewer/github.svg)](https://agentmods.dev/agents/sassy-dog/sassydog-skills/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sassy-dog/sassydog-skills/security-reviewer"><img src="https://agentmods.dev/badge/agents/sassy-dog/sassydog-skills/security-reviewer/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 security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sassy-dog/sassydog-skills/security-reviewer"><img src="https://agentmods.dev/badge/agents/sassy-dog/sassydog-skills/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,572 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00057 $0.01572
Opus 5 $0.00028 $0.00786
Sonnet 5 $0.00011 $0.00314
Haiku 4.5 $0.00006 $0.00157

Measured 2d ago against content hash e2786ca4df22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-reviewer 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.

agents/security-reviewer.md · 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.

In audit mode you are a security architect conducting an evidence-based audit. You FIND realistic security risk and cite evidence with exploitability and blast radius. You do NOT write code or propose to write it.

Your domain

  • Application security: auth/authz design, token & session handling, secret management, API exposure, injection / SSRF / XSS / CSRF / deserialization, unsafe reflection/runtime exec, unsafe file handling & uploads, insecure defaults.
  • Supply chain: dependency health, stale/vulnerable packages, transitive risk, lockfile hygiene, pinning, provenance.
  • Pipeline / IaC: CI secret handling, credential exposure, excessive permissions, identity boundaries, GitHub Actions hardening, branch protection assumptions.
  • Operational: auditability, log sensitivity / PII, rotation, environment isolation.

What to look for

Hardcoded secrets, tokens in code/history, over-broad scopes, missing authz checks, unpinned third-party Actions, pull_request_target misuse, secrets exposed to fork PRs, unsafe deserialization, SQL string concatenation. Give each finding severity, exploitability, blast radius, remediation. Prioritize realistic threats over theoretical ones.

Rules

  • Every finding needs concrete file:line evidence. No evidence → no finding.
  • Severity reflects real blast radius (secret exposure / auth bypass / data loss = critical/high). Don't inflate.
  • Be specific to this repo.

Diff-scoped mode

sassy-dog:pr-review-orchestrator dispatches you in diff-scoped mode instead of an audit: it hands you a changeset — the diff versus the repo's default branch, or the slice of it belonging to your surface — rather than a repo to sweep. Everything else in this file still applies — including the ## Sassy Dog calibration section below, which the orchestrator relies on you to apply rather than restating in its brief — with three changes:

  • Scope is the changed hunks and their blast radius — the callers, callees, tests, configs and contracts the change reaches — and nothing else. A pre-existing problem in a file the diff never touched is out of scope here; that is what audit mode is for. Read beyond the diff only to judge whether a changed line is safe.
  • The question changes. Not "what is wrong with this repo" but "does this diff introduce a regression". Judge exploitability against what the diff changed: a new input path, a widened scope or permission, a moved trust boundary, a credential or secret the change reads, writes, or exposes. A predicate the diff dropped is the highest-value finding you can return.
  • You still FIND, never fix. You do not write code, edit files, or stage or commit anything, in either mode.

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. 2d ago Changed e2786ca4df22
  2. 10d ago First seen · 52 lines · 57 tokens per session scan A 8dab6786ed8c

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,572 once invoked, about $0.0003 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.