| Medium | AutoPilot's local sandbox buffers unbounded stdout and stderrGHSA-xm4r-96wv-34m5 | 2026-11-17 | See advisory |
| Medium | Any signed-up user can make the platform pay for unlimited Ideogram/Replicate agent-thumbnail image generations, with no charge, balance check or per-user limitGHSA-x4vp-rcwv-9hx4 | 2026-11-17 | See advisory |
| Medium | Credit top-up refunds and lost disputes leave credits spendable until the webhook, and treat Stripe's cents as creditsGHSA-wwfj-25jr-ffg4 | 2026-11-17 | See advisory |
| Medium | Anyone with a chat share link can read secrets in tool-call arguments and large tool results that skip redactionGHSA-wmfr-wj7p-4v99 | 2026-11-17 | See advisory |
| Medium | A captured Exa Websets webhook delivery can be replayed at any time to re-run the owner's triggered workflowGHSA-wfr2-333w-xrqc | 2026-11-17 | See advisory |
| Medium | AutoPilot credit check race: run_capability can run a paid block many times, or for free, for the price of oneGHSA-v77v-f222-gp6g | 2026-11-17 | See advisory |
| High | Unbounded request-validation errors stall the REST API and write rejected request bodies to the logGHSA-v39w-3j4r-c33g | 2026-11-17 | See advisory |
| Medium | Open Redirect via Unvalidated redirect_uri in OAuth Authorize PageGHSA-rr95-66gw-xm5f | 2026-11-17 | See advisory |
| Medium | DNS-rebinding TOCTOU in Ollama LLM provider endpoint validation allows SSRF to internal servicesGHSA-rmj7-pw6w-hf33 | 2026-11-17 | See advisory |
| High | AutoGPT Platform Backend: MCPToolBlock Auto-Lookup Lets a Shared Agent's Author Use the Runner's MCP CredentialsGHSA-rjgp-whm3-w5mj | 2026-11-17 | See advisory |
| Medium | Regular Expression Denial of Service (ReDoS) in GitHub CI Results Block (search_pattern)GHSA-rcc6-v5j6-rw4j | 2026-11-17 | See advisory |
| Medium | Failed or stopped LLM block calls can refund the full credit charge after the provider already received the requestGHSA-r9jq-jjw9-49j6 | 2026-11-17 | See advisory |
| Medium | Open Redirect in OAuth authorize endpoint via unvalidated error redirectsGHSA-r87r-9p73-r6v6 | 2026-11-17 | See advisory |
| Medium | An approved marketplace listing can run its installer's own workflows as the installer, with the author's inputsGHSA-r833-g67j-55gc | 2026-11-17 | See advisory |
| High | OAuth Redirect URI Leads to JavaScript ExecutionGHSA-r326-2hff-vh8g | 2026-11-17 | See advisory |
| Medium | Public webhook endpoints buffer large unauthenticated bodies before verificationGHSA-r2xf-4rwf-26r7 | 2026-11-17 | See advisory |
| Medium | Office preview expands an unbounded embedded ZIP thumbnailGHSA-qxw2-mr3h-jf6g | 2026-11-17 | See advisory |
| Medium | Host-scoped credential headers leaked to other hosts through HTTP redirectsGHSA-qx75-7566-5phx | 2026-11-17 | See advisory |
| Medium | Browser SSRF via unguarded redirects, subsequent navigation and DNS re-resolutionGHSA-q5jq-5368-v5cf | 2026-11-17 | See advisory |
| Medium | SendEmailBlock SMTP DNS rebinding bypasses SSRF blocklistGHSA-px96-3j32-c68c | 2026-11-17 | See advisory |
| High | Anyone with an Exa Search Monitor trigger's URL can start its workflow with fake events, even with a secret setGHSA-pc98-63jj-97gm | 2026-11-17 | See advisory |
| Medium | A workflow that runs itself as a sub-workflow fills every executor worker, blocking other users' runsGHSA-p55h-7x25-pp6g | 2026-11-17 | See advisory |
| Critical | A user can add a version under another user's workflow ID and take over its Marketplace listingGHSA-mwr6-g4xq-4rvp | 2026-11-17 | See advisory |
| Medium | AutoPilot never cleans up the media files its block runs write to the executor's disk, so a user can fill itGHSA-jqh7-c84w-36vf | 2026-11-17 | See advisory |
| Medium | Any member of a Slack workspace, Telegram group or Teams team can link it to their own AutoGPT accountGHSA-hwcj-243r-mp6x | 2026-11-17 | See advisory |
| Medium | Credentials followed a redirect off-origin when the Location header hid the new host behind a backslashGHSA-hp9v-vh5x-5jv3 | 2026-11-17 | See advisory |
| Low | TOCTOU Race Condition in Refresh Token RotationGHSA-h67f-cg97-pj37 | 2026-11-17 | See advisory |
| Critical | Any signed-up user can reach other users' AgentMail inboxes and Exa Websets through the platform's shared vendor keysGHSA-gfrp-hrh7-x8x8 | 2026-11-17 | See advisory |
| Medium | Offboarded members can still execute org-billed presets and retained webhooks after org removalGHSA-g7j2-3x5v-7x7v | 2026-11-17 | See advisory |
| Medium | Template rendering was not bounded in size or timeGHSA-f4f5-9hp8-cprw | 2026-11-17 | See advisory |
| Medium | Unbounded response buffering in the HTTP helper: memory-exhaustion DoS on URL downloadsGHSA-crrx-44jx-c4q8 | 2026-11-17 | See advisory |
| High | A Slack workspace member can make the Slack bot send its bot token to their server and fetch internal URLsGHSA-cc2m-58f6-pg2c | 2026-11-17 | See advisory |
| Medium | Sandbox file extraction has no cumulative byte or file-count limitGHSA-98g6-r386-569h | 2026-11-17 | See advisory |
| Medium | Presets and triggers on another user's workflow ran and were billed in that workflow owner's organizationGHSA-8x6w-2c8v-c57j | 2026-11-17 | See advisory |
| High | An EXECUTE_BLOCK-only API key or OAuth token could run AutoPilotBlock through the external API and get a full, unattended AutoPilot turn with the key owner's stored credentials, agents and workspaceGHSA-8vm3-rxfw-5867 | 2026-11-17 | See advisory |
| Medium | AutoMod timeouts bypass moderation when automodfailopen=FalseGHSA-8mgj-2rcx-pwm4 | 2026-11-17 | See advisory |
| High | Denial of service and SSRF via a JSON Schema nested in MCPToolBlock and AgentExecutorBlock inputsGHSA-8c79-3c9x-p2v6 | 2026-11-17 | See advisory |
| Medium | AutoPilot tool calls, dry runs and chat-bot turns spend/run past the platform's own usage, concurrency and duration capsGHSA-8752-6cg5-wf78 | 2026-11-17 | See advisory |
| Medium | Open redirect in the OAuth callback route: the "next" parameter was not sanitized (incomplete fix of GHSA-j2cp-jg5q-38wj)GHSA-7pv2-q2ff-2wx6 | 2026-11-17 | See advisory |
| Medium | SSRF blocklist gap: IPv6 transition prefixes (6to4 / Teredo / NAT64 / IPv4-translated) reach embedded IPv4 endpoints via Requests wrapperGHSA-7334-956w-67pg | 2026-11-17 | See advisory |
| Medium | AutoGPT Platform E2B code-execution blocks leave sandboxes running on the operator's shared credential far past what the block actually charges forGHSA-6jc8-g72m-gf95 | 2026-11-17 | See advisory |
| Medium | Denial of service via unbounded format Jinja filter width in TextFormatter (un-patched sibling of GHSA-ppw9)GHSA-5238-wm28-5fvf | 2026-11-17 | See advisory |
| Medium | LLM and other dynamically-priced blocks run free when a priced input is left at its schema defaultGHSA-4jw5-mmcx-c2rr | 2026-11-17 | See advisory |
| High | Personal-organization conversion race lets users bill agent runs to another user's wallet or evade LLM usage chargesGHSA-47r2-jjh5-pcgh | 2026-11-17 | See advisory |
| Medium | A member removed from an organization keeps creating workflows in it with an API key made while a memberGHSA-458m-58gm-8cr9 | 2026-11-17 | See advisory |
| Medium | AutoPilot's approval gate and workflow review pause can be bypassed via resume, sub-session delegation, and run_agent version driftGHSA-389q-9q6m-8pxm | 2026-11-17 | See advisory |
| Medium | Marketplace and shared agents can redirect a user's saved SMTP or database login to a server the agent's author controlsGHSA-35gg-95rx-c8fm | 2026-11-17 | See advisory |
| Medium | One user can stall other users' workflow runs by leaving executor workers stuck in a video encode or email sendGHSA-2jw6-9qj6-7pr9 | 2026-11-17 | See advisory |
| Medium | Billing-manager-only members are treated as ordinary members and can read other team members' runsCVE-2026-129984 · GHSA-6f2g-95mv-mgwv | 2026-11-16 | See advisory |
| Medium | Anyone with an active OAuth app's client ID can stall the REST API by sending wrong client secretsCVE-2026-129317 · GHSA-fp4g-p7j5-v6pw | 2026-11-16 | See advisory |
| Medium | A crafted CSV file referenced in AutoPilot can freeze the process running the chatGHSA-q2g2-67rp-2c5r | 2026-11-12 | See advisory |
| High | Exposure of Sensitive Information to an Unauthorized Actor and Improper Enforcement of Behavioral Workflow in AutoGPTGHSA-xfwx-rhmm-rjqc | 2026-10-29 | See advisory |
| Medium | Public chat share leaks secrets stored under camelCase keys (redaction bypass)GHSA-x9c2-wpmm-2mx4 | 2026-10-29 | See advisory |
| Medium | ReDoS in MatchTextPatternBlock via unbounded user-supplied regexGHSA-qrmh-27g7-9cp2 | 2026-10-28 | See advisory |
| Medium | Quadratic-time ReDoS in XMLParserBlock via the gravitasml tokenizerGHSA-847j-hphx-v6f3 | 2026-10-28 | See advisory |
| Low | Concurrent chat file download can restore access after AutoGPT share revocationGHSA-qv8m-h6gh-rj66 | 2026-10-27 | See advisory |
| Medium | Billing vulnerability: failed nested tool calls refund credits that were never chargedGHSA-p835-fqv4-4x3m | 2026-10-27 | See advisory |
| High | AutoPilot: chat text was pre-processed by the Claude Code CLI (slash commands and file mentions)GHSA-hf7q-6hwp-f6v2 | 2026-10-27 | See advisory |
| Medium | Billing Vulnerability: AutoPilot runs paid blocks on the operator's credential without charging creditsGHSA-f3mw-f2qc-wh9m | 2026-10-27 | See advisory |
| High | SSRF: the unspecified address :: bypasses the request blocklist and reaches loopback servicesGHSA-3c7g-v5hv-wwv4 | 2026-10-27 | See advisory |
| Medium | The Sentry tunnel forwards first-party cookies, including the session token, to Sentry's ingestGHSA-2739-q98r-hx72 | 2026-10-27 | See advisory |
| High | Hardcoded Default Fernet Encryption Key Exposes All Stored OAuth CredentialsGHSA-57mf-wqwq-6g6x | 2026-10-05 | See advisory |
| Critical | Hardcoded Default JWT Secret Enables Complete Authentication BypassGHSA-24q6-6h89-f9p7 | 2026-10-05 | See advisory |
| High | Webhook provider path confusion bypasses generic webhook secret verificationCVE-2026-72922 · GHSA-349p-3c3r-8mjr | 2026-08-05 | See advisory |
| Medium | Preset creation can bind a foreign webhook, enabling known-ID forged victim webhook executions and exposing its signing secretGHSA-4m2w-qfr5-9f3v | 2026-07-21 | See advisory |
| Medium | AutoGPT Classic: HTTP client domain allowlist bypass via userinfo and backslash URL tricksGHSA-xxpr-ccx5-48mf | 2026-07-14 | See advisory |
| High | AutoGPT Classic: SSRF in llamafile setup script via unvalidated download URL and redirectsGHSA-vm4v-5hgj-rq77 | 2026-07-14 | See advisory |
| High | AutoGPT Classic: SSRF in web fetch commands via missing internal/private address validationGHSA-vj3m-g4cv-8j93 | 2026-07-14 | See advisory |
| High | AutoGPT Classic: GitHub credentials sent to arbitrary hosts via clone_repository URLGHSA-c543-3829-f27q | 2026-07-14 | See advisory |
| Low | AutoGPT Classic: litellm version constraint permitted compromised releases (supply chain)GHSA-4hqw-7f5j-5v66 | 2026-07-14 | See advisory |
| High | AutoGPT Classic: incomplete URL validation in forge allows SSRF in browser commandsGHSA-3cwv-4w3r-xqff | 2026-07-14 | See advisory |
| Medium | IDOR in Webhook Ping Endpoint Allows Enumeration and Cross-User Ping TriggeringCVE-2026-56823 · GHSA-rq9m-xvc7-v9h6 | 2026-06-26 | See advisory |
| High | SSRF in SendWebRequestBlock via IPv4-mapped IPv6 / CGNAT IP-validation bypassCVE-2026-56663 · GHSA-8qc5-rhmg-r6r6 | 2026-06-24 | See advisory |
| High | Denial of Service (DoS) via Resource Exhaustion in text templating featuresCVE-2026-33235 · GHSA-ppw9-h7rv-gwq9 | 2026-06-23 | See advisory |
| Medium | User-controlled regex in ExtractTextInformationBlock produces O(n^2) output, enabling memory-exhaustion DoSCVE-2025-32423 · GHSA-pppq-xx2w-7jpq | 2026-06-23 | See advisory |
| Medium | Quadratic memory amplification in AITextSummarizerBlock chunking (DoS via attacker-controlled max_tokens/overlap)CVE-2025-32394 · GHSA-955p-gpfx-r66j | 2026-06-23 | See advisory |
| High | DOM-Based XSS and Open Redirect in AutoGPT SignUp PageCVE-2026-55237 · GHSA-j2cp-jg5q-38wj | 2026-06-17 | See advisory |
| Critical | There is a DoS vulnerability in MediaDurationBlockCVE-2025-32437 · GHSA-rg6v-m9x9-7wf9 | 2026-06-11 | See advisory |
| High | There is a DoS vulnerability in AddAudioToVideoBlockCVE-2025-32436 · GHSA-g26x-xwc5-7p44 | 2026-06-11 | See advisory |
| Critical | There is a DoS vulnerability in ScreenshotWebPageBlockCVE-2025-32424 · GHSA-7g34-7fvq-xxq6 | 2026-06-11 | See advisory |
| Critical | There is a DoS vulnerability in FileStoreBlock with StepThroughItemsBlockCVE-2025-32422 · GHSA-9fr4-9jj9-mhh6 | 2026-06-11 | See advisory |
| Critical | There is a DoS vulnerability in LoopVideoBlockCVE-2025-32392 · GHSA-267x-8jx3-gg6w | 2026-06-11 | See advisory |
| Medium | SendEmailBlock allows SSRF via user-controlled SMTP server, bypassing IP blocklistCVE-2026-33234 · GHSA-4jwj-6mg5-wrwf | 2026-05-13 | See advisory |
| Medium | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-32425 · GHSA-vw3v-whvp-33v5 | 2026-05-13 | 0.6.32 |
| Medium | Credit system bypassed via direct block execution in POST /api/blocks/{block_id}/executeCVE-2026-45023 · GHSA-8pjg-mfqm-vrhr | 2026-05-11 | See advisory |
| High | Unsafe Redis cache deserialization (pickle.loads) would allow backend RCE in case of cache poisoningCVE-2026-33233 · GHSA-rfg2-37xq-w4m9 | 2026-05-11 | See advisory |
| High | Unauthenticated DoS via Disk Space ExhaustionCVE-2026-33232 · GHSA-374w-2pxq-c9jp | 2026-05-11 | See advisory |
| High | Authenticated Session Hijacking via IDORCVE-2026-30950 · GHSA-q58p-v9r9-7gqj | 2026-05-11 | See advisory |
| Critical | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2026-26020 · GHSA-4crw-9p35-9x54 | 2026-02-12 | 0.6.48 |
| Medium | ReDoS (Regular Expression Denial of Service) at Code Extraction BlockGHSA-m2wr-7m3r-p52c | 2026-02-10 | See advisory |
| Medium | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2026-26006 | 2026-02-10 | 0.6.32 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-32393 · GHSA-5cqw-g779-9f9x | 2026-02-05 | 0.6.32 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2026-22038 · GHSA-rc89-6g7g-v5v7 | 2026-02-04 | 0.6.46 |
| Critical | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-62616 · GHSA-ggc4-4fmm-9hmc | 2026-02-04 | 0.6.34 |
| Critical | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-62615 · GHSA-r55v-q5pc-j57f | 2026-02-04 | 0.6.34 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2026-24780 · GHSA-r277-3xc5-c79v | 2026-01-29 | 0.6.44 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents.CVE-2025-53944 · GHSA-x77j-qg2x-fgg6 | 2025-07-30 | See advisory |
| Low | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-31494 · GHSA-958f-37vw-jx8f | 2025-04-15 | 0.6.1 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-31491 · GHSA-ggcm-93qg-gfhp | 2025-04-15 | 0.6.1 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-31490 · GHSA-wvjg-9879-3m7w | 2025-04-14 | 0.6.1 |
| High | AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE).CVE-2025-1040 | 2025-03-20 | 0.4.0 |
| High | A Server-Side Request Forgery (SSRF) vulnerability was identified in the Requests utility of significant-gravitas/autogpt versions prior to v0.4.0.CVE-2025-0454 | 2025-03-20 | 0.4.0 |
| Critical | A command injection vulnerability exists in the workflow-checker.yml workflow of significant-gravitas/autogpt.CVE-2024-8156 | 2025-03-20 | 0.5.1 |
| High | AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows.CVE-2025-22603 · GHSA-4c8v-hwxc-2356 | 2025-03-10 | 0.4.2 |
| Critical | A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings.CVE-2024-6091 | 2024-09-11 | See advisory |
| Critical | AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements used in an OS command ('OS Command Injection') due to a flaw in its shell command validation function.CVE-2024-1881 | 2024-06-06 | 0.5.1 |
| High | An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gravitas/autogpt project, affecting versions up to v0.5.0.CVE-2024-1880 | 2024-06-06 | 0.5.1 |
| High | A Cross-Site Request Forgery (CSRF) vulnerability in significant-gravitas/autogpt version v0.5.0 allows attackers to execute arbitrary commands on the AutoGPT server.CVE-2024-1879 | 2024-06-06 | See advisory |
| Low | Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model.CVE-2023-37275 · GHSA-r7f7-qrrv-3fjh | 2023-07-13 | 0.4.3 |
| High | Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model.CVE-2023-37274 · GHSA-5h38-mgp9-rj5f | 2023-07-13 | 0.4.3 |
| High | Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model.CVE-2023-37273 · GHSA-x5gj-2chr-4ch6 | 2023-07-13 | 0.4.3 |