authorized-security-router

authorized-security-router is a skill for Codex from markoblogo/abvx-agent-skills. It costs 78 tokens per session (1,263 once invoked), scanned A, original, MIT.

A routing procedure for authorized defensive security reviews and reverse analysis of software, devices, files, or APIs.

In plain words
What is it for?
Use it to choose a safe analysis route for APKs, binaries, JavaScript, firmware, malware samples, APIs, language-model systems, or supply-chain reviews.
Why use it?
It clarifies what may be inspected and prevents accidental movement into unauthorized access, live exploitation, credential extraction, or scope expansion.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to choose a safe analysis route for APKs, binaries, JavaScript, firmware, malware samples, APIs, language-model systems, or supply-chain reviews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markoblogo/abvx-agent-skills/authorized-security-router
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 markoblogo/abvx-agent-skills --skill authorized-security-router
Clone the repo
git clone --depth 1 https://github.com/markoblogo/abvx-agent-skills

Made for: 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 authorized-security-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/authorized-security-router/github.svg)](https://agentmods.dev/skills/markoblogo/abvx-agent-skills/authorized-security-router)
Your own site
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/authorized-security-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/authorized-security-router/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 authorized-security-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/authorized-security-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/authorized-security-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,263 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00078 $0.01263
Opus 5 $0.00039 $0.00632
Sonnet 5 $0.00016 $0.00253
Haiku 4.5 $0.00008 $0.00126

Measured 10d ago against content hash 26109595521c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

authorized-security-router 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 10d 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/authorized-security-router/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authorized Security Router

Route security work before acting. This skill is for authorized defensive analysis, triage, and reporting. It is not an exploitation, evasion, credential, persistence, phishing, or C2 playbook.

Scope Gate

Before selecting a route, establish:

  • authorization: own system, internal review, client-approved scope, CTF/lab, or inspect-only public repository/artifact review;
  • target boundary: repository, app, package, binary, API, URL, firmware image, sample hash, or document set;
  • action level: inspect-only, local static analysis, local sandbox analysis, browser verification, report-only, or remediation planning;
  • prohibited actions: no unauthorized access, no destructive testing, no live exploitation, no credential extraction, no persistence, no evasion, no phishing, no C2, no scope expansion.

Public review means inspect-only review of public repositories or static artifacts. It does not authorize interacting with public URLs, third-party apps, production APIs, login flows, or browser-driven security testing. URL, app, API, and browser-facing security routes require own-system, client-approved, internal, or lab/CTF authorization.

If scope is unclear or the request asks for offensive execution, stop and ask for a safer authorized framing.

Allowed Routes

Use the smallest defensive route that fits the task:

Target / intent Route Pair with
APK or mobile app review Manifest, permissions, redacted secret indicators, network endpoints, package metadata, static call-chain notes evidence-ledger-research
Static binary triage File metadata, strings, imports, symbols, packer indicators, suspicious capability inventory evidence-ledger-research
Frontend JS security review Source maps, bundled endpoints, dangerous DOM sinks, token handling, request signing logic, redacted secret indicators browser-verification, web-quality-audit
Firmware or IoT inventory Filesystem layout, services, redacted credential indicators, exposed configs, SBOM hints, update mechanism notes evidence-ledger-research
Malware or suspicious sample triage Hashes, strings, YARA/Sigma candidate indicators, behavior hypotheses, sandbox-safe report plan evidence-ledger-research
API or GraphQL audit Auth boundaries, object-level access checks, token handling, schema exposure, unsafe defaults web-quality-audit when browser-facing
LLM or agent security review Prompt injection surface, tool permission boundaries, data exfil paths, memory poisoning risks agents-best-practices
Supply chain audit SBOM, dependency risk, redacted secret indicators, CI/CD exposure, package provenance, release integrity delivery-preflight-gate
Security issue intake Classify severity, affected surface, evidence needed, next actor, and remediation owner repo-issue-triage

Read the full file on GitHub · 119 lines

Files

What ships with it

2 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. 10d ago First seen · 119 lines · 78 tokens per session scan A 26109595521c

Subscribe to this mod's changes

authorized-security-router is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,263 once invoked, about $0.0004 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.