Approved changes feed: RSS · Atom

cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:*

part: a version: * update: *

VendorAgpt (1f783fc9-c798-5fd7-8b08-5e28f17d7f5b)
ProductAutogpt Platform (e7dfa3eb-74f7-5dfa-a5f5-d8a44407440c)
Edition*
Language*
Software edition*
Target software*
Target hardware*
Other*
NotesImported from gcve-enriched-dumps CVE data

PURL mappings

PURLSourceLast updated
No PURL mappings for this CPE yet.

Vulnerability references

IdentifiercpeApplicabilitySubmitteddb.gcve.eu detailsRationale
CVE:CVE-2026-26006 vulnerable 2026-06-08 07:53:20.697198 Redos (Regular Expression Denial of Service) at Code Extraction Block in significant-gravitas/autogpt
MEDIUM (6.5)
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. The autogpt before 0.6.32 is vulnerable to Regular Expression Denial of Service due to the use of regex at Code Extraction Block. The two Regex are used containing the corresponding dangerous patterns \s+[\s\S]*? and \s+(.*?). They share a common characteristic — the combination of two adjacent quantifiers that can match the same space character (\s). As a result, an attacker can supply a long sequence of space characters to trigger excessive regex backtracking, potentially leading to a Denial of Service (DoS). This vulnerability is fixed in 0.6.32.
Published: 2026-02-10T21:21:00.635Z
Updated: 2026-02-11T21:27:22.085Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2026-24780 vulnerable 2026-06-08 07:51:18.165366 AutoGPT is Vulnerable to RCE via Disabled Block Execution
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.
Published: 2026-01-29T17:39:33.524Z
Updated: 2026-01-29T21:16:08.779Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2026-22038 vulnerable 2026-06-08 07:49:17.591603 AutoGPT's API Keys and Secrets Logged in Plaintext in Stagehand Integration Blocks
HIGH (8.1)
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-v0.6.46, the AutoGPT platform's Stagehand integration blocks log API keys and authentication secrets in plaintext using logger.info() statements. This occurs in three separate block implementations (StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock) where the code explicitly calls api_key.get_secret_value() and logs the result. This issue has been patched in autogpt-platform-beta-v0.6.46.
Published: 2026-02-04T22:28:20.401Z
Updated: 2026-02-05T15:04:13.893Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-62616 vulnerable 2026-06-08 07:39:16.219543 AutoGPT has SSRF vulnerability in SendDiscordFileBlock
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-v0.6.34, in SendDiscordFileBlock, the third-party library aiohttp.ClientSession().get is used directly to access the URL, but the input URL is not filtered, which will cause SSRF vulnerability. This issue has been patched in autogpt-platform-beta-v0.6.34.
Published: 2026-02-04T22:28:40.783Z
Updated: 2026-02-05T15:01:02.149Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-62615 vulnerable 2026-06-08 07:39:16.218976 AutoGPT has SSRF vulnerability in ReadRSSFeedBlock
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-v0.6.34, in RSSFeedBlock, the third-party library urllib.request.urlopen is used directly to access the URL, but the input URL is not filtered, which will cause SSRF vulnerability. This issue has been patched in autogpt-platform-beta-v0.6.34.
Published: 2026-02-04T22:28:37.041Z
Updated: 2026-02-05T15:02:20.452Z
Reference links
Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-32393 vulnerable 2026-06-08 07:18:59.710680 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-31494 vulnerable 2026-06-08 07:18:57.969744 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-31491 vulnerable 2026-06-08 07:18:57.930242 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-31490 vulnerable 2026-06-08 07:18:57.929695 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-1040 vulnerable 2026-06-08 07:06:36.692035 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data
CVE:CVE-2025-0454 vulnerable 2026-06-08 07:02:24.627890 db.gcve.eu details were skipped to keep the page responsive. Imported from gcve-enriched-dumps CVE data

Contribute

You can submit an edit proposal for this CPE entry or suggest a related product/vendor addition using the action button above.