security

security is an agent for coding agents from AndrewAltimit/template-repo. It costs 0 tokens per session (4,511 once invoked), scanned B, a copy of security-detailed, Unlicense.

Security documentation for an AI-agent system. It describes checks for user authorization, suspicious instructions, code insertion, workflow access, and action logging.

In plain words
What is it for?
Use it to design, review, or operate agent workflows with authorization checks, limited access, validation, and an audit trail.
Why use it?
It helps ensure agents fail safely and do not perform or submit actions without permission.

Agent

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 agents/andrewaltimit/template-repo/security
Clone the repo
git clone --depth 1 https://github.com/AndrewAltimit/template-repo

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 security

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewaltimit/template-repo/security.svg)](https://agentmods.dev/agents/andrewaltimit/template-repo/security)
Your own site
<a href="https://agentmods.dev/agents/andrewaltimit/template-repo/security"><img src="https://agentmods.dev/badge/agents/andrewaltimit/template-repo/security.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,511 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00000 $0.04511
Opus 5 $0.00000 $0.02256
Sonnet 5 $0.00000 $0.00902
Haiku 4.5 $0.00000 $0.00451

Measured 4d ago against content hash 3f9c0933ba62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security scanned grade B with 2 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 4d 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.

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 -sSL https://raw.githubusercontent.com/AndrewAltimit/template-repo/main/tools/rust/gh-validator/install.sh | bash

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.

curl -sSL https://raw.githubusercontent.com/AndrewAltimit/template-repo/main/tools/rust/gh-validator/install.sh | bash
Origin

This is a copy

89% identical to security-detailed — 401 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/agents/security.md · 507 lines

How it starts

The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agents Security Documentation

Overview

The agents system implements a comprehensive security model designed to prevent unauthorized use, prompt injection attacks, and malicious code insertion. The system uses multiple layers of defense including user authentication, keyword-based command triggers, and real-time commit validation during PR processing.

Core Security Principles

  1. Zero Trust by Default: No action is taken without explicit authorization
  2. Defense in Depth: Multiple security layers that work independently
  3. Audit Trail: All actions are logged with user attribution
  4. Fail Secure: Any security failure results in no action taken
  5. Real-time Validation: Continuous security checks during execution

Security Features

1. Multi-Layer Security Implementation

Our agents implement defense-in-depth with multiple security layers:

Workflow-Level Security (First Layer)
  • GitHub Actions if conditions prevent workflows from running for unauthorized users
  • Fail-fast security checks terminate workflows immediately for unauthorized access
  • Minimal GITHUB_TOKEN permissions following principle of least privilege
Application-Level Security (Second Layer)
  • Allow List Based Authorization: Only specific GitHub usernames can trigger agent actions
  • Rate Limiting: Prevents abuse with configurable request limits per user
  • Repository Validation: Restricts agents to specific repositories
  • Comprehensive Security Checks: All layers validated before any action

2. Agent Admins

The agent admins list is configured in .agents.yaml under the security.agent_admins field. Only these users can trigger agent actions via [Action][Agent] keywords. The repository owner (extracted from GITHUB_REPOSITORY environment variable) is always included automatically.

Agent Admin Capabilities

Agent admins have the following special capabilities:

  1. Trigger Agent Actions: Use [Action][Agent] keywords to invoke agents
  2. Extend Iteration Limits: Use [CONTINUE] to allow more agent iterations (see below)
  3. Authoritative Comments: Their comments are treated as authoritative in review contexts

Read the full file on GitHub · 507 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. 4d ago First seen · 507 lines · 0 tokens per session scan B 3f9c0933ba62

Subscribe to this mod's changes

security is an agent published in the GitHub repository AndrewAltimit/template-repo (131 stars, last pushed 2mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 4,511 tokens. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). It is 89% identical to security-detailed, differing in 401 lines, and is treated as a copy.

Related

Other agents, from other repositories

agent-system

An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.

OrlojHQ/orloj · 0 tokens

ai-safety-auditor

AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP LLM compliance.

yonatangross/orchestkit · 37 tokens

guardian

The Guardian is the last line of defense between your code and production. It runs a multi-dimensional quality gate that checks tests, type safety, security, code quality, and documentation coverage in a single pass. Unlike a CI pipeline that tells you something broke 10 minutes after you pushed, the Guardian catches…

nxtg-ai/forge-plugin · 0 tokens

compliance

The Compliance agent protects your project from legal and regulatory risk. It audits dependency licenses for compatibility (is that GPL-3.0 package going to force your MIT project open-source?), checks data handling against GDPR requirements (do you have a data inventory? can users request deletion?), verifies WCAG…

nxtg-ai/forge-plugin · 0 tokens

crucible-detective

The CRUCIBLE Detective performs forensic audits on test suites to find the gap between claimed quality and actual quality. It was born from a real incident: a project with 1,601 "passing" tests and 77% "claimed coverage" that turned out to have approximately 15% actual coverage, 439 mocks, 66+ hollow assertions, and…

nxtg-ai/forge-plugin · 0 tokens

detective

The Detective is a forensic analyst for your codebase. It does not fix things -- it finds things. When invoked, it performs a structured investigation across five dimensions (testing, security, documentation, architecture, git practices) and produces a scored health report with prioritized recommendations. Every…

nxtg-ai/forge-plugin · 0 tokens