# CVE-2026-48168: PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name

> Attackers can execute arbitrary shell commands in GitHub Actions runners via unquoted PR branch names, potentially compromising repository access and OIDC tokens.

- **Severity:** Critical 10.0 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 5 Aug 2026
- **Updated:** 5 Aug 2026
- **Also known as:** GHSA-xp85-6wwf-r67c

## What is CVE-2026-48168?

CVE-2026-48168 is a critical command injection vulnerability in MervinPraison PraisonAI, published on 5 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official description

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow allows any @claude comment to trigger the job regardless of whether the commenter is a trusted collaborator. An outside contributor can open a pull request from a fork whose branch name contains shell metacharacters and comment @claude, causing Bash to execute arbitrary shell code in the GitHub Actions runner. Because these commands run in a job holding a GitHub App token with write permissions, OIDC access, and gh/git access, the injection can be chained through $GITHUB_PATH to compromise later privileged steps, enabling repository writes, pull request and issue manipulation, or OIDC-token abuse. This issue has been fixed in version 4.6.40.

Weakness: CWE-862 (Missing Authorization)

## Which versions are affected by CVE-2026-48168?


## How do I fix CVE-2026-48168?

No fix has been published for CVE-2026-48168 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-48168 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-48168 exists.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-48168 and fix it if it is affected.

What it is: CVE-2026-48168 is a critical command injection vulnerability in MervinPraison PraisonAI, published on 5 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-48168 exists.

Affected product: MervinPraison PraisonAI. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-48168/ (Markdown: https://insights.sbomify.com/CVE-2026-48168/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-48168
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-48168
- OSV: https://osv.dev/vulnerability/CVE-2026-48168

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-48168/
Summaries are generated and may contain mistakes; the official description above is the record.