CVE-2026-57124: Improper Neutralization of Special Elements used in an OS Command

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

CVE-2026-56839: Improper Limitation of a Pathname to a Restricted Directory

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the CODETOOLS wrappers keep workspaceroot as None and pass workspace=None to readfile, searchreplace, and applydiff helpers that enforce path containment only for a truthy workspace. An application that exposes codereadfile,...

CVE-2026-57130: Improper Input Validation

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/emailtools.py interpolates LLM-controlled fromaddr, subject, and query values directly into quoted IMAP SEARCH criteria. Embedded quote, backslash, newline, or null characters can...

CVE-2026-57126: Server-Side Request Forgery (SSRF)

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, SpiderTools.validateurl calls hostisblocked, which checks literal host encodings but does not resolve DNS names before scrapepage, crawl, extractlinks, extracttext, or URL-mention fetches connect. An attacker-controlled...

CVE-2026-57131: Improper Control of Generation of Code

PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.createapp mounts praisonai.jobs.router.createrouter under /api/v1/runs without authentication or per-job authorization. Network clients can submit attacker-controlled prompts and agent configuration, list and read job...

CVE-2026-57125: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agentyaml, and the approve field can mark executecommand as YAML-approved before @requireapproval checks critical tools. This...

CVE-2026-57115: Server-Side Request Forgery (SSRF)

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, SpiderTools.scrapepage validates only the initial URL and lets requests.Session.get follow redirects automatically, so a public-looking URL can redirect to a loopback, private, link-local, or metadata address without...

CVE-2026-57132: Improper Authentication

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...

CVE-2026-57129: Improper Limitation of a Pathname to a Restricted Directory

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, MentionsParser.processfilemention accepts file-mention values and falls back from workspace-relative resolution to Pathfilepath without traversal, symlink, or workspace-boundary validation. Prompt input from users, bots, or...

CVE-2026-57120: Protection Mechanism Failure

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, executecode sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.formatmap to resolve dotted fields through C-level attribute access that bypasses safegetattr. This exposes class,...

CVE-2026-57119: Improper Limitation of a Pathname to a Restricted Directory

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the unauthenticated Jobs API accepts an absolute or traversing agentfile path in POST /api/v1/runs and passes it to the job executor without a workspace allowlist or boundary check. A remote caller can cause the server to open files...

CVE-2026-57127: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. Prior to 4.6.58, recipe serve installs APIKeyAuthMiddleware or JWTAuthMiddleware when an operator selects api-key or JWT authentication, but each middleware forwards requests when PRAISONAIAPIKEY or PRAISONAIJWTSECRET and the corresponding recipe value are...

PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret

SummaryThe PraisonAI Recipe HTTP server silently allows unauthenticated requests when auth is configured as api-key or jwt but the corresponding secret is missing.This creates an authentication fail-open condition. An operator can start the Recipe server with authentication enabled, including on ...

PraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)

Summarypraisonai/browser/server.py validates incoming WebSocket connections using a Chromeextension Origin check. The regex chrome-extension://a-z0-932 is applied withre.match, which only anchors at the start of the string, not the end. Any Originheader with more than 32 alphanumeric characters...

PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete

SummaryPraisonAI's async Jobs API the FastAPI service in praisonai/jobs/ installs its router with no authentication middleware, no router-level dependency, and no per-route auth check. Any caller who can reach the jobs server can submit agent jobs executed against the operator's configured LLM...

PYSEC-2026-3886 PraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)

Summary praisonai/browser/server.py validates incoming WebSocket connections using a Chrome extension Origin check. The regex chrome-extension://a-z0-932 is applied with re.match, which only anchors at the start of the string, not the end. Any Origin header with more than 32 alphanumeric characte...

PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

SummaryThe PraisonAI MCP server exposes an HTTP-stream transport praisonai mcp serve --transport http-stream that binds to localhost and, by default, has no API key. Its only access control for browser-originated requests is an Origin allowlist, which the code implements as required by the MCP...

PYSEC-2026-3889 PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret

Summary The PraisonAI Recipe HTTP server silently allows unauthenticated requests when auth is configured as api-key or jwt but the corresponding secret is missing. This creates an authentication fail-open condition. An operator can start the Recipe server with authentication enabled, including o...

PYSEC-2026-3892 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

Summary The PraisonAI MCP server exposes an HTTP-stream transport praisonai mcp serve --transport http-stream that binds to localhost and, by default, has no API key. Its only access control for browser-originated requests is an Origin allowlist, which the code implements as required by the MCP...

PYSEC-2026-3885 PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete

Summary PraisonAI's async Jobs API the FastAPI service in praisonai/jobs/ installs its router with no authentication middleware, no router-level dependency, and no per-route auth check. Any caller who can reach the jobs server can submit agent jobs executed against the operator's configured LLM...