{"id":"CVE-2026-48168","aliases":["EUVD-2026-53575","GHSA-xp85-6wwf-r67c"],"status":"published","title":"PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name","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.","severity":{"version":"3.1","score":10,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.01503,"percentile":0.74508,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-862"],"published":"2026-08-05T18:29:38Z","modified":"2026-10-28T02:31:06Z","products":[{"vendor":"mervinpraison","product":"praisonai"}],"references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c","tags":["x_refsource_CONFIRM","exploit","advisory"]},{"url":"https://github.com/MervinPraison/PraisonAI/commit/179cab02dbec0c1e9b601507a659","tags":["x_refsource_MISC","fix"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/48xxx/CVE-2026-48168.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-48168","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-48168","title":"PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name","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.","status":"published","published":"2026-08-05T18:29:38.632Z","modified":"2026-08-05T19:24:05.128Z","cvss":[{"version":"3.1","score":10,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"cna"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T13:50:49.872037Z"}],"euvd":[{"id":"EUVD-2026-53575","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.","status":"published","published":"2026-08-05T18:29:38Z","modified":"2026-08-05T19:24:05Z","cvss":[{"version":"3.1","score":10,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"updated_at":"2026-11-02T18:02:09.520152Z"}],"nvd":[{"id":"CVE-2026-48168","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.","status":"published","published":"2026-08-05T19:17:31.07Z","modified":"2026-10-23T21:10:00.157Z","cvss":[{"version":"3.1","score":10,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"secondary"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T14:12:35.031043Z"}],"osv":[{"id":"CVE-2026-48168","title":"PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name","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.","status":"published","published":"2026-08-05T18:29:38.632Z","modified":"2026-10-28T02:31:06.445562302Z","cvss":[{"version":"3.1","score":10,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T15:45:06.701612Z"}]}}