AutoGPT is Vulnerable to RCE via Disabled Block Execution
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.6.44
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: poc
- Automatable: yes
- Technical impact: total
Summary
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.44, AutoGPT Platform's block execution endpoints (both main web API and external API) allow executing blocks by UUID without checking the `disabled` flag. Any authenticated user can execute the disabled `BlockInstallationBlock`, which writes arbitrary Python code to the server filesystem and executes it via `import()`, achieving Remote Code Execution. In default self-hosted deployments where Supabase signup is enabled, an attacker can self-register; if signup is disabled (e.g., hosted), the attacker needs an existing account. autogpt-platform-beta-v0.6.44 contains a fix.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: poc · Automatable: yes · Technical impact: total
- Record last updated
Affected versions
- Significant-Gravitas AutoGPT
From 0.1.0 · fixed in 0.6.44
- agptPyPI
through 0.2.2
References 6
GitHub · Significant-Gravitas/AutoGPT
- Advisory GHSA-r277-3xc5-c79v
- autogpt_platform/backend/backend/api/external/v1/routes.py · L79-L93
- autogpt_platform/backend/backend/api/features/v1.py · L1408-L1424
- autogpt_platform/backend/backend/api/features/v1.py · L355-L395
- autogpt_platform/backend/backend/blocks/block.py · L15-L78
- autogpt_platform/backend/backend/data/block.py · L459