What is river-review-security-audit?

An entry procedure for a deliberate security audit of a repository or subsystem. A security audit is a focused search for weaknesses using source evidence rather than running the target code.

Use it for guidance, a focused component review, or a full repository audit when the user explicitly requests one.

It keeps the audit scope explicit and separates broad security assessment from the smaller security review normally done for one pull request.

river-review-security-audit — Skill for Claude Code by s977043

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.

Any agent

npx skills add s977043/river-review --skill river-review-security-audit

Clone the repo

git clone --depth 1 https://github.com/s977043/river-review

Made for: Claude Code.

Or install river-review, the plugin that ships this one along with the rest of its 139 skills, 18 commands, 5 agents, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/s977043/river-review/river-review-security-audit/github.svg)](https://agentmods.dev/skills/s977043/river-review/river-review-security-audit)

Your own site

<a href="https://agentmods.dev/skills/s977043/river-review/river-review-security-audit"><img src="https://agentmods.dev/badge/skills/s977043/river-review/river-review-security-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/s977043/river-review/river-review-security-audit"><img src="https://agentmods.dev/badge/skills/s977043/river-review/river-review-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,501 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.

Model	Per session	Once invoked
Fable 5.1	$0.00103	$0.03501
Opus 5.5	$0.00041	$0.01400
Sonnet 5.5	$0.00021	$0.00700
Haiku 4.5	$0.00010	$0.00350

Measured 1mo ago against content hash 8c616fda9795, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

river-review-security-audit 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 1mo 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.

plugin-dist/river-review/skills/agent-skills/river-review-security-audit/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit Entry

Inspired by Cloudflare's security-audit-skill, but implemented as a River Review-native entry skill rather than a vendored audit engine.

This skill is the explicit entry point for repository or subsystem security audit work. It does not replace river-review-security, the normal diff-oriented security review entry.

When to Use

Use this skill only when the user explicitly asks for a security audit beyond an ordinary PR review. Typical requests include repository-wide security audit, subsystem security audit, security assessment, or a bounded source review of a security-sensitive surface.

Do not select this skill for a generic request such as "review this PR for security". Route that request to river-review-security.

Modes

Select exactly one mode before reviewing.

guidance: use when the user wants methodology, planning, or an audit approach. Explain the method and constraints. Do not claim that audit work was executed.
focused: use when the user names a bounded subsystem, path, component, or security surface. Freeze that scope and review only source evidence inside the boundary.
full-audit: use only when the user explicitly requests repository-wide audit coverage. Perform repository reconnaissance and source review across the repository. Semantic coverage is observe-only and never a safety guarantee.

If the request does not clearly justify full-audit, use focused or guidance.

Non-negotiable Source-only Policy

Version 0.5.0 is source-only.

Allowed evidence collection:

file reads
repository code search
static diff inspection
repository metadata and dependency manifests
configuration and documentation inspection
static history inspection when it supports source provenance

Prohibited execution:

package installation or dependency fetching
target repository build scripts
target repository test commands
package lifecycle scripts
dev servers or application startup
browsers or emulators that execute target code
fuzzing or dynamic probes
requests to production, shared, or external endpoints
use of ambient credentials to reproduce a finding

Read the full file on GitHub · 400 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/attack-classes.json 11 KB

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.

1mo ago Changed · +61 lines · +8 tokens per session 8c616fda9795
1mo ago First seen · 339 lines · 95 tokens per session scan A 20ba0b6f8ace

Subscribe to this mod's changes

river-review-security-audit is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 3,501 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-17.

Claude Code Code review Security adversarial-review ai-code-review audit claude-code-plugin codex entry midstream routing source-only

river-review-security-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
river-review-security-audits977043/river-review	Skill	7	today	MIT	A	103	Claude Code
logic-reviewhyhmrright/logic-lens	Skill	25	8d ago	MIT	A	161	Claude Code
logic-healthhyhmrright/logic-lens	Skill	25	8d ago	MIT	A	180	Claude Code
run-iteration-evalhyhmrright/logic-lens	Skill	25	8d ago	MIT	A	108	Claude Code
sync-skill-cachehyhmrright/logic-lens	Skill	25	8d ago	MIT	A	103	Claude Code
bump-versionhyhmrright/logic-lens	Skill	25	8d ago	MIT	A	52	Claude Code
logic-locatehyhmrright/logic-lens	Skill	25	8d ago	MIT	A	177	Claude Code