PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters
CVE-2026-57130 · GHSA-c969-5x3p-vq3v · published 2026-06-18 · updated 2026-07-20
- Severity
- High
- CVSS score
- 8.1
- Chance of exploitation (EPSS)
- 0.46%
- Fixed in
- 1.6.59
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
An attacker who can craft prompts that cause an LLM agent to call searchemails with injection payloads can: Terminate IMAP connections (denial of service) Inject arbitrary IMAP commands — including LIST (enumerate folders), SELECT (switch folders), FETCH (read emails from other mailboxes), STORE (modify flags), COPY/MOVE (move emails), DELETE/EXPUNGE (permanently delete emails) Exfiltrate email contents from folders the user did not intend to expose to the agent Permanently delete emails via injected DELETE + EXPUNGE commands The attack requires the IMAP backend to be configured (EMAILADDRESS + EMAIL_PASSWORD env vars), which is a documented and common deployment for email-capable agents.
Upgrade praisonaiagents to 1.6.59 or later.
1. Escape double-quote characters in IMAP parameters. Per RFC 3501, literal strings use {n}\r\n format or quoted strings with \ escaping: 2. Use IMAP literal syntax ({n}\r\ndata) instead of quoted strings for all user-controlled parameters. This prevents any injection regardless of content. 3. Apply the escaping to all IMAP search criteria parameters: fromaddr, subject, query, and searchid/message_id.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonaiagents | PyPI | <= 1.6.48 | 1.6.59 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalPraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secretspraisonaiagents
- CriticalPraisonAI: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
- CriticalPraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired inpraisonaiagents
- CriticalPraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpointspraisonaiagents
- CriticalPraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)praisonaiagents, praisonai
- CriticalPraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessionspraisonaiagents, praisonai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.