adversarial-security

adversarial-security is a skill for Claude Code, Codex from neverinfamous/memory-journal-mcp. It costs 161 tokens per session (1,701 once invoked), scanned A, original, MIT.

A multi-step security review of an entire code repository that models threats, tests possible attacks, and plans fixes with checks for practical impact.

In plain words
What is it for?
Use it for repository-wide security audits, threat modeling, red-team analysis, vulnerability investigation, and release or compliance reviews. It also includes checks specific to MCP servers.
Why use it?
It reduces the chance of overlooking an attack path when reviewing a large project with many inputs, interfaces, or dependencies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/neverinfamous/memory-journal-mcp/adversarial-security
Any agent
npx skills add neverinfamous/memory-journal-mcp --skill adversarial-security
Clone the repo
git clone --depth 1 https://github.com/neverinfamous/memory-journal-mcp

Made for: Claude Code, Codex.

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 adversarial-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/adversarial-security.svg)](https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/adversarial-security)
Your own site
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/adversarial-security"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/adversarial-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,701 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 5.1 $0.00161 $0.01701
Opus 5 $0.00081 $0.00851
Sonnet 5 $0.00032 $0.00340
Haiku 4.5 $0.00016 $0.00170

Measured 6d ago against content hash d367855794a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

adversarial-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 6d 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.

skills/adversarial-security/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Security

A multi-pass security auditing system that produces high-confidence vulnerability assessments by introducing structured adversarial critique stages. Audits pass through an iterative pipeline of reconnaissance, red-team attack, remediation planning, and optional external validation — producing output optimized for exploitability, impact, and actionable remediation.

When to Load

Load this skill when any of these apply:

  • Running a security audit against an entire repository
  • Performing threat modeling for a new or existing codebase
  • The user asks for an adversarial security review or red-team analysis
  • The user says "security audit", "threat model", "find vulnerabilities", "adversarial security", or "red team this repo"
  • Preparing a security posture report for a release or compliance review
  • You want to reduce blind spots in your own security assessment

Auto-Detection

Before starting, auto-detect the project type by scanning the repository:

Signal Project Type Extra Categories
MCP SDK imports (@modelcontextprotocol/sdk), tools/list handler, tool description fields mcp-server MCP-Specific Security (Category 10) — full depth
Express/Hono/Fastify imports, HTTP route handlers, listen() calls web-app Transport & Network (Category 5) — full depth
bin field in package.json, CLI arg parsing (yargs, commander, meow) cli-tool Input Validation (Category 3) — extra CLI focus
No server/CLI signals, only exports library Supply Chain (Category 9) — extra consumer focus

The MCP-Specific Security category (Category 10) is always evaluated with graceful degradation. If the target is not an MCP server, findings in this category are reported as informational rather than skipped entirely. The rationale: even non-MCP projects may expose tool-like interfaces, schema descriptions, or configuration metadata that could be poisoned.

Read the full file on GitHub · 150 lines

Files

What ships with it

7 files 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.

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. 6d ago First seen · 150 lines · 161 tokens per session scan A d367855794a0

Subscribe to this mod's changes

adversarial-security is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 161 tokens to every session and 1,701 once invoked, about $0.0008 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 skills, from other repositories

system-audit

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims to have delivered — followed by immediate cheap-safe fixes and a ranked backlog. Use when the user says 'аудит системы', 'проверь себя', 'самопроверка', 'system…

awrshift/agent-memory-kit · 225 tokens

run-orchestrator

Execute 5-phase TDD workflow for complex features. Use when the user invokes /run, asks to build/create/implement a feature, requests a complex multi-file change, or types 'fasttrack:'. Enforces phase gates, sprint contracts, and builder!=reviewer discipline.

nguyenthienthanh/aura-frog · 62 tokens

tech-writing

Write professional technical documents — requirements/PRD, tech spec/design doc, low-level design, decision records, and trade-off analysis — at a formality tier matched to the task. Grounds every claim in real code or a cited source, marks what it could not verify, and refuses to pad. Use when asked to write/update a…

nguyenthienthanh/aura-frog · 88 tokens

perf-profiling

Systematic performance profiling and optimization across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async), and database (EXPLAIN ANALYZE, indexing) layers. Use when the user reports slow code, latency, memory leaks, needs to benchmark, or wants to speed up an application. Measure…

nguyenthienthanh/aura-frog · 107 tokens

plan-orchestrator

Route hierarchical-planning intents to the correct backing script. Use when the user invokes /aura-frog:plan (with or without subcommand), mentions plan verbs (expand/next/replan/promote/archive/freeze/thaw/undo/status/conflicts), or types a plan-vocabulary bare word with .claude/plans/active.json present. Owns verb…

nguyenthienthanh/aura-frog · 91 tokens

tree-of-thoughts

Structured reasoning — branch/evaluate/prune/expand search over solution space (tree), or a single ordered chain when the path is linear. Use for architecture with multi-step decisions, refactor planning, complex debug hypothesis trees, or step-by-step structured thinking. Papers: Yao et al. 2023 (ToT)…

nguyenthienthanh/aura-frog · 80 tokens