agent-guard

agent-guard is a skill for Codex from elliottwaves-20/agent-guard. It costs 400 tokens per session (6,790 once invoked), scanned C, original, MIT.

A security-scanning skill for checking third-party agent skills, plugins, and MCP servers before installation. MCP is a standard way for an AI agent to connect to external tools and services.

In plain words
What is it for?
Use it to inspect skill files, MCP source code, installation scripts, and package sources, with optional checks of a running MCP server.
Why use it?
Third-party add-ons run with your account's permissions and could contain prompt injection, credential theft, data theft, or backdoors. The scan helps identify those risks before the code is installed.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it to inspect skill files, MCP source code, installation scripts, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elliottwaves-20/agent-guard/agent-guard
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 elliottwaves-20/agent-guard --skill agent-guard
Clone the repo
git clone --depth 1 https://github.com/elliottwaves-20/agent-guard

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 agent-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/elliottwaves-20/agent-guard/agent-guard.svg)](https://agentmods.dev/skills/elliottwaves-20/agent-guard/agent-guard)
Your own site
<a href="https://agentmods.dev/skills/elliottwaves-20/agent-guard/agent-guard"><img src="https://agentmods.dev/badge/skills/elliottwaves-20/agent-guard/agent-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 400 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,790 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 5 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 $0.00400 $0.06790
Opus 5 $0.00200 $0.03395
Sonnet 5 $0.00080 $0.01358
Haiku 4.5 $0.00040 $0.00679

Measured today against content hash 7bd8893cc912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

agent-guard scanned grade C with 5 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 today.

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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl | bash` install scripts and cargo crate sources.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find "$HOME/.claude/plugins/cache" -name "SKILL.md" -not -path "*/node_modules/*" \

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find "$HOME/.claude/skills" -maxdepth 2 -name "SKILL.md" \

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$WORKDIR"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

malcontent), curl|bash install scripts via the SkillSpector static scan. Use
SKILL.md · 595 lines

How it starts

The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-guard — scan first, install after

Skills and MCP servers are third-party code that runs with your user account's permissions. A malicious one can read SSH keys, .env files, and browser profiles, exfiltrate them, or hijack the agent itself through a poisoned SKILL.md. This skill makes a security scan the mandatory first step of every installation.

Because skills follow the open SKILL.md standard and MCP is an open protocol, the scan is agent-agnostic: one verdict covers Claude Code, Codex, Gemini/Antigravity, Hermes, OpenClaw, and any other compatible agent — and the installer deploys the same audited commit to all of them in one step.

Professional scanners do the work, each where it is strongest:

  • NVIDIA SkillSpector — skill scans and the static MCP source scan. One tool for both, with 71 vulnerability patterns (prompt injection, data exfiltration, privilege escalation, MCP tool poisoning / least-privilege, supply chain with live OSV.dev CVE lookup, bundled hooks/settings), taint tracking, YARA, hidden/nested-archive inspection, and LLM analysis through the user's own coding-agent CLI login (no API key) or a hosted provider. Also covers curl | bash install scripts and cargo crate sources.
  • cisco-ai-mcp-scanner — the optional live runtime MCP check (scan_mcp.py --sandbox / remote). A static scan cannot see MCP tools that a server only registers at runtime; this starts the server in a sandbox to inspect them.
  • Datadog GuardDog — CLI-tool package scans (npm/PyPI/Go/cargo) via scan_cli.py; malware heuristics + YARA + registry metadata, run through the official Docker image on Windows.
  • VirusTotal + malcontent — release binaries via scan_cli.py binary: hash reputation, optionally (--deep) a capability analysis.

Read the full file on GitHub · 595 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. today Changed · +16 lines · +25 tokens per session 7bd8893cc912
  2. 6d ago First seen · 579 lines · 375 tokens per session scan C e7a3fd3d8376

Subscribe to this mod's changes

agent-guard is a skill published in the GitHub repository elliottwaves-20/agent-guard (2 stars, last pushed yesterday), licensed MIT. It adds 400 tokens to every session and 6,790 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it C with 5 findings (downloads and executes remote code, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

clinical-trial-protocol-skill

Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…

Agent-Threat-Rule/agent-threat-rules · 70 tokens

claude-d3js-skill

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

Agent-Threat-Rule/agent-threat-rules · 25 tokens

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…

Agent-Threat-Rule/agent-threat-rules · 89 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens

create-auth-skill

Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.

Agent-Threat-Rule/agent-threat-rules · 66 tokens

prior-auth-review-skill

Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…

Agent-Threat-Rule/agent-threat-rules · 63 tokens