caro safety.instructions.md

caro safety.instructions.md is an instructions file for GitHub Copilot from wildcard/caro. It costs 1,135 tokens per session, scanned C, original, AGPL-3.0.

Review guidance for checking code against safety and security requirements, including dangerous patterns and required pattern validation.

In plain words
What is it for?
Use it during safety-focused code reviews to check critical concerns and verify required matching rules.
Why use it?
It helps reveal risky code patterns before they can cause security or operational problems.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

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 instructions/wildcard/caro/safety
Clone the repo
git clone --depth 1 https://github.com/wildcard/caro

Made for: GitHub Copilot.

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 caro safety.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wildcard/caro/safety.svg)](https://agentmods.dev/instructions/wildcard/caro/safety)
Your own site
<a href="https://agentmods.dev/instructions/wildcard/caro/safety"><img src="https://agentmods.dev/badge/instructions/wildcard/caro/safety.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,135 This file is loaded in full into every session.
When invoked 1,135 The same file — it is already loaded in full.
Security scan C 4 findings. Scan, not verified.
Origin unknown 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 $0.01135 $0.01135
Opus 5 $0.00567 $0.00567
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 2d ago against content hash 993ac9cad664, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

caro safety.instructions.md scanned grade C with 4 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 2d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `sudo su`, `sudo -i` - Shell escalation

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

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`, `wget | sh` - Remote code execution

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 /` - Recursive root deletion

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 | bash`, `wget | sh` - Remote code execution
.github/instructions/safety.instructions.md · 160 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 160 lines · 1,135 tokens per session scan C 993ac9cad664

Subscribe to this mod's changes

caro safety.instructions.md is an instructions file published in the GitHub repository wildcard/caro (37 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 1,135 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.