reviewing-detection-rules-for-evasion

reviewing-detection-rules-for-evasion is a skill for Claude Code from UnboundCompute/security-agent-skills. It costs 176 tokens per session (1,923 once invoked), scanned A, original, MIT.

A review of detection rules against variations an attacker could use, such as different casing, spacing, quoting, paths, flag order, or encoding.

In plain words
What is it for?
Use it to test existing detection-as-code rules and find bypasses in their matching logic and exclusions.
Why use it?
A rule can match one spelling of suspicious activity while missing another spelling that has the same effect.

Skill for Claude Code

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

Part of the security-agent-skills plugin — 194 skills shipped together

Good fit Use it to test existing detection-as-code rules and find bypasses in their matching logic and exclusions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion
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 UnboundCompute/security-agent-skills --skill reviewing-detection-rules-for-evasion
Clone the repo
git clone --depth 1 https://github.com/UnboundCompute/security-agent-skills

Made for: Claude Code.

Or install security-agent-skills, the plugin that ships this one along with the rest of its 194 skills.

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 reviewing-detection-rules-for-evasion

README.md
[![agentmods](https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion/github.svg)](https://agentmods.dev/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion)
Your own site
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion/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 reviewing-detection-rules-for-evasion

Your own site · 80×15
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/reviewing-detection-rules-for-evasion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,923 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 $0.00176 $0.01923
Opus 5.5 $0.00070 $0.00769
Sonnet 5.5 $0.00035 $0.00385
Haiku 4.5 $0.00018 $0.00192

Measured 1mo ago against content hash 591875908a6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewing-detection-rules-for-evasion 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.

skills/reviewing-detection-rules-for-evasion/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing detection rules for evasion: whether the rule survives an attacker who reads it

A detection rule is a guard, and like any guard it is only as strong as the exactness of the thing it checks against what the attacker can vary. Detection content is often written to match one observed spelling of an attack: a specific command line, a known tool name, a particular flag. An attacker who can read the rule, or simply reason about it, expresses the same action a different way and walks past. This review treats a rule the way an attacker treats a filter: find the field it trusts, find the variant it does not cover, and produce an event that does the malicious thing without tripping the match. The attacker-controlled field is the source, the rule's match logic is the guard, and a bypass is the bug.

When to use

  • You maintain detection-as-code rules and want to know which are brittle before an attacker does.
  • Rules match on attacker-controlled fields: command lines, arguments, user-agents, paths, names.
  • You are reviewing or threat-modeling existing detections, not writing new ones.

Scope check

Test evasion only against detections, telemetry, and systems you own or are authorized to assess, and generate malicious-looking events only where that is expected and coordinated. A realistic bypass event can trigger a real response. If you can't name the authorization, stop.

The loop

  1. Inventory each rule and the field it trusts. For every detection rule, identify the fields it matches on and which of those an attacker controls freely: a process command line and its arguments, environment values, a user-agent, a file path or name. A rule keyed on an attacker-controlled field is only as strong as how exactly it pins that field against every equivalent form.

  2. Test literal and encoding variants. For each match, ask whether the same malicious action can be expressed a way the rule does not cover: alternate casing, quoting, extra whitespace, an equivalent path or name form, reordered flags, an encoded argument, or a different tool that has the same effect. A rule that matches one literal spelling misses every synonym of it.

Read the full file on GitHub · 132 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. 1mo ago First seen · 132 lines · 176 tokens per session scan A 591875908a6a

Subscribe to this mod's changes

reviewing-detection-rules-for-evasion is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 1,923 once invoked, about $0.0007 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 2026-09-05.

Related

Other skills, from other repositories

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…

FarzamHabibi/pre-production-checklist · 72 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-tanstack-ai

Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…

arcjet/arcjet-js · 103 tokens

integrate-arcjet-guard-claude-managed-agents

Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…

arcjet/arcjet-js · 102 tokens

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens

varlock-claude-skill

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.

Agent-Threat-Rule/agent-threat-rules · 28 tokens