bouncer copilot-instructions.md

bouncer copilot-instructions.md is an instructions file for GitHub Copilot from karanb192/bouncer. It costs 475 tokens per session, scanned F, original, MIT.

Safety instructions for a coding agent that block destructive shell commands, such as deleting broad folders, formatting disks, exposing secrets, or destroying Git history.

In plain words
What is it for?
Preventing dangerous commands during coding tasks, including irreversible file deletion, unsafe system changes, secret exposure, and forced Git history rewrites.
Why use it?
They reduce the risk of an agent damaging files, systems, repositories, or credentials while working in a terminal.

Instructions file for GitHub Copilot

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/karanb192/bouncer/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/karanb192/bouncer

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 bouncer copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/karanb192/bouncer/copilot-instructions.svg)](https://agentmods.dev/instructions/karanb192/bouncer/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/karanb192/bouncer/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/karanb192/bouncer/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 475 This file is loaded in full into every session.
When invoked 475 The same file — it is already loaded in full.
Security scan F 6 findings. Scan, not verified.
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 $0.00475 $0.00475
Opus 5 $0.00237 $0.00237
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 4d ago against content hash d9d81db9e144, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

bouncer copilot-instructions.md scanned grade F with 6 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- Exfiltrates secrets: `curl -d @.env ...`, `curl -T id_rsa ...`, posting to paste/exfil hosts.

Asks for rootmediumPrivilege escalation

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

- Deletes broadly or irrecoverably: `rm -rf /`, `rm -rf ~`, `rm -rf .`, `rm -rf *`, `rm -rf --no-preserve-root /`, `sudo rm -rf`, deleting `node_modules ../../*` or parent/glob targets.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Exposes secrets: `cat .env`, `cat ~/.ssh/id_rsa`, `printenv`, `echo $AWS_SECRET_ACCESS_KEY`.

Downloads and executes remote codehighSupply chain

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

- Pipes a URL straight to a shell (RCE): `curl ... | sh`, `wget -qO- ... | bash`.

Recursive force deletehighDestructive command

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

- Deletes broadly or irrecoverably: `rm -rf /`, `rm -rf ~`, `rm -rf .`, `rm -rf *`, `rm -rf --no-preserve-root /`, `sudo rm -rf`, deleting `node_modules ../../*` or parent/glob targets.

Makes network callslowCapability

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

- Pipes a URL straight to a shell (RCE): `curl ... | sh`, `wget -qO- ... | bash`.
.github/copilot-instructions.md · 22 lines

What it actually says

Bouncer: destructive-command guardrails

Bouncer enforces these rules at the door via a fail-closed preToolUse hook. This list is the advisory, defense-in-depth layer: do not propose or run any of the following destructive shell commands. The hook will deny them anyway, so don't waste a turn.

Never run a command that:

  • Deletes broadly or irrecoverably: rm -rf /, rm -rf ~, rm -rf ., rm -rf *, rm -rf --no-preserve-root /, sudo rm -rf, deleting node_modules ../../* or parent/glob targets.
  • Writes to or formats a raw disk device: dd of=/dev/sd*, mkfs.*, wipefs -a /dev/*, echo ... > /dev/sda.
  • Overwrites protected system files: chmod 777 /etc/passwd, chmod -R 777 /, chown -R ... /, echo ... > /etc/passwd.
  • Spawns a fork bomb (:(){ :|:& };:) or kills init (kill -9 1).
  • Rewrites or destroys git history/remote: git push --force origin main, git reset --hard, git clean -fdx.
  • Pipes a URL straight to a shell (RCE): curl ... | sh, wget -qO- ... | bash.
  • Exfiltrates secrets: curl -d @.env ..., curl -T id_rsa ..., posting to paste/exfil hosts.
  • Exposes secrets: cat .env, cat ~/.ssh/id_rsa, printenv, echo $AWS_SECRET_ACCESS_KEY.
  • Destroys a database/store: DROP TABLE/DATABASE/SCHEMA, TRUNCATE, un-WHERE'd DELETE/UPDATE, redis-cli flushall, dropdb.
  • Performs an irreversible release/data loss: npm publish, docker volume rm.

If a task seems to require one of these, stop and ask the user first. Prefer scoped, reversible alternatives (a WHERE clause, --force-with-lease, a dry run).

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 · 22 lines · 475 tokens per session scan F d9d81db9e144

Subscribe to this mod's changes

bouncer copilot-instructions.md is an instructions file published in the GitHub repository karanb192/bouncer (5 stars, last pushed 17d ago), licensed MIT. It adds 475 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it F with 6 findings (sends data to an external url, asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.