PraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocation

AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation SummaryPraisonAI's AgentOS FastAPI deployment surface remains unauthenticated incurrent main and in releases after the published patched version forGHSA-pm96-6xpr-978x / CVE-2026-40151.The public...

PraisonAI GitHub template cache path traversal allows outside-cache file write and directory deletion

SummaryPraisonAI's template loader accepts GitHub template URIs with refs, for examplegithub:owner/repo/[email protected]. The resolver stores the user-controlledtemplate path and ref verbatim, and the cache layer later joins those values into/.praison/cache/templates/github//// withoutnormalizing...

PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary SummaryPraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

PraisonAI: Missing Authentication for Critical Function and Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai

Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands SummaryPraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host apps without authentication. A remote unauthenticated client can send POST /api/mcp/connect with a comma...

PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp & Linear bots)

The WhatsApp and Linear bot adapters verify the inbound webhook HMAC signature onlywhen a secret is configured. When the secret environment variable is unset — thedefault on a fresh install and common in development — verification is skipped entirelyand the webhook body is parsed and dispatched a...

PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

SummaryThe email search tool in src/praisonai-agents/praisonaiagents/tools/emailtools.py constructs IMAP SEARCH commands by interpolating LLM-controlled parameters fromaddr, subject, query directly into IMAP protocol strings using f-string formatting with double-quote delimiters. An attacker who...

PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints

PraisonAI AgentTeam.launch exposes unauthenticated remote agent invocation endpoints SummaryPraisonAI's documented Python AgentTeam.launch / Agents.launch HTTP server starts externally reachable agent invocation endpoints without any authentication enforcement.The current implementation registers...

PYSEC-2026-3513 praisonai: recipe serve auth middleware silently disables itself when no secret is set

praisonai: recipe serve authentication middleware silently disables itself when no secret is set Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Target: https://github.com/MervinPraison/PraisonAI --- Package: praisonai on PyPI Version tested: 4.6.48...

PYSEC-2026-3501 PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

Unauthenticated Remote Code Execution via Jobs API and Approval Bypass in PraisonAI Summary An unauthenticated attacker can execute arbitrary OS commands on any server running the PraisonAI Jobs API by submitting a crafted workflow YAML. The attack chains two weaknesses: the /api/v1/runs endpoint...

PYSEC-2026-3519 PraisonAI: Jobs webhook SSRF protection bypass via DNS rebinding

Jobs webhook SSRF protection bypass via DNS rebinding Summary PraisonAI's Async Jobs API validates webhookurl when a job request is parsed and again when the internal Job object is constructed. That validation blocks direct loopback/private targets, but it is not bound to the later network reques...

PYSEC-2026-3529 PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

Unauthenticated Remote Code Execution via Jobs API and Approval Bypass in PraisonAI Summary An unauthenticated attacker can execute arbitrary OS commands on any server running the PraisonAI Jobs API by submitting a crafted workflow YAML. The attack chains two weaknesses: the /api/v1/runs endpoint...

PYSEC-2026-3533 PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder

Summary The executecode tool's subprocess sandbox advertises a three-layer defense AST validation, text-pattern blocklist, restricted builtins. In sandbox mode the default only two layers are active — the text-pattern blocklist is skipped — and both remaining layers are bypassed by combining two...

PYSEC-2026-3535 praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS

praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Target: https://github.com/MervinPraison/PraisonAI Weakness: CWE-918 Server-Side Request Forgery SSRF. --- Summary The SSRF gua...

PYSEC-2026-3511 PraisonAI: Jobs API exposes agent-execution endpoints with no authentication

praisonai: Jobs API exposes agent-execution endpoints with no authentication Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Target: https://github.com/MervinPraison/PraisonAI --- Package: praisonai on PyPI Affected version empirically tested: 4.6.48...

PYSEC-2026-3527 PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal

Summary The MentionsParser in src/praisonai-agents/praisonaiagents/tools/mentions.py processes @file: mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path...

PYSEC-2026-3536 PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired in

The MCP SSE server started via ToolsMCPServer.runsse / launchtoolsmcpservertransport="sse" binds to 0.0.0.0 by default and builds its Starlette application with no authentication middleware and no Origin-header validation. The module mcp/mcpsecurity.py provides exactly the needed controls origin...

PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

Unauthenticated Remote Code Execution via Jobs API and Approval Bypass in PraisonAI Summary An unauthenticated attacker can execute arbitrary OS commands on any server runningthe PraisonAI Jobs API by submitting a crafted workflow YAML. The attack chains twoweaknesses: the /api/v1/runs endpoint...

praisonai: recipe serve auth middleware silently disables itself when no secret is set

praisonai: recipe serve authentication middleware silently disables itself when no secret is setResearcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security ResearchTarget: https://github.com/MervinPraison/PraisonAI---Package: praisonai on PyPIVersion tested: 4.6.48.File:...

PraisonAI: Jobs webhook SSRF protection bypass via DNS rebinding

Jobs webhook SSRF protection bypass via DNS rebinding SummaryPraisonAI's Async Jobs API validates webhookurl when a job request is parsedand again when the internal Job object is constructed. That validation blocksdirect loopback/private targets, but it is not bound to the later networkrequest...

praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS

praisonaiagents: SSRF guard validates literal IPs only and never resolves DNSResearcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security ResearchTarget: https://github.com/MervinPraison/PraisonAIWeakness: CWE-918 Server-Side Request Forgery SSRF.--- SummaryThe SSRF guard...