Praisonai
by Praison
Source repositories
CVEs (103)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-39888 | Cri | 0.64 | 9.9 | 0.00 | Apr 8, 2026 | PraisonAI is a multi-agent teams system. Prior to 1.5.115, execute_code() in praisonaiagents.tools.python_tools defaults to sandbox_mode="sandbox", which runs user code in a subprocess wrapped with a restricted __builtins__ dict and an AST-based blocklist. The AST blocklist… | ||
| CVE-2026-57145 | cri | 0.59 | — | — | Jun 18, 2026 | ## Summary The `multiedit` tool in `src/praisonai/praisonai/tools/multiedit.py` allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments… | ||
| CVE-2026-57140 | cri | 0.59 | — | — | Jun 18, 2026 | ## Summary The published npm package `praisonai` ships a TypeScript `AgentOS` HTTP server that defaults to `host: "0.0.0.0"` and registers sensitive agent routes without any authentication or authorization middleware. When a developer starts `AgentOS`, a network attacker who… | ||
| CVE-2026-57141 | cri | 0.59 | — | — | Jun 18, 2026 | ## Summary The `codeMode` tool in `src/praisonai-ts/src/tools/builtins/code-mode.ts` uses `new Function()` with a `with(sandbox)` pattern to execute LLM-generated code. The blocklist-based "sandbox" can be trivially bypassed via `Function('return this')()` to recover the global… | ||
| CVE-2026-57124 | cri | 0.59 | — | — | Jun 18, 2026 | # Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands ## Summary PraisonAI 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… | ||
| CVE-2026-57118 | cri | 0.59 | — | — | Jun 18, 2026 | # PraisonAI `AgentTeam.launch()` exposes unauthenticated remote agent invocation endpoints ## Summary PraisonAI's documented Python `AgentTeam.launch()` / `Agents.launch()` HTTP server starts externally reachable agent invocation endpoints without any authentication… | ||
| CVE-2026-57131 | cri | 0.59 | — | — | Jun 18, 2026 | # 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… | ||
| CVE-2026-57127 | cri | 0.59 | — | — | Jun 18, 2026 | # 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:**… | ||
| CVE-2026-57125 | cri | 0.59 | — | — | Jun 18, 2026 | # 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… | ||
| CVE-2026-47410 | Cri | 0.57 | 9.8 | 0.00 | Jul 21, 2026 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an insecure default cryptographic key. The JWT signing secret defaults to the hardcoded literal `"dev-secret-change-me"` when `PLATFORM_JWT_SECRET` is unset. A… | ||
| CVE-2026-47396 | Cri | 0.57 | 9.8 | 0.00 | Jul 21, 2026 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by… | ||
| CVE-2026-47393 | Cri | 0.57 | 9.8 | 0.00 | Jul 21, 2026 | PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented… | ||
| CVE-2026-47392 | Cri | 0.57 | 9.9 | 0.01 | Jul 21, 2026 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to… | ||
| CVE-2026-47391 | Cri | 0.57 | 9.8 | 0.01 | Jul 21, 2026 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A… | ||
| CVE-2026-41497 | Cri | 0.57 | 9.8 | 0.01 | May 8, 2026 | PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution… | ||
| CVE-2026-40315 | Cri | 0.57 | 9.8 | 0.00 | Apr 14, 2026 | PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the table_prefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization.… | ||
| CVE-2026-40288 | Cri | 0.57 | 9.8 | 0.01 | Apr 14, 2026 | PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run <file.yaml> loads a YAML file with… | ||
| CVE-2026-39890 | Cri | 0.57 | 9.8 | 0.01 | Apr 8, 2026 | PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags (such as !!js/function and !!js/undefined). This allows an attacker to craft a malicious YAML file… | ||
| CVE-2026-34935 | Cri | 0.57 | 9.8 | 0.01 | Apr 3, 2026 | PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop,… | ||
| CVE-2026-34934 | Cri | 0.57 | 9.8 | 0.01 | Apr 3, 2026 | PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the get_all_user_threads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via update_thread. When the application… |
- risk 0.64cvss 9.9epss 0.00
PraisonAI is a multi-agent teams system. Prior to 1.5.115, execute_code() in praisonaiagents.tools.python_tools defaults to sandbox_mode="sandbox", which runs user code in a subprocess wrapped with a restricted __builtins__ dict and an AST-based blocklist. The AST blocklist…
- risk 0.59cvss —epss —
## Summary The `multiedit` tool in `src/praisonai/praisonai/tools/multiedit.py` allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments…
- risk 0.59cvss —epss —
## Summary The published npm package `praisonai` ships a TypeScript `AgentOS` HTTP server that defaults to `host: "0.0.0.0"` and registers sensitive agent routes without any authentication or authorization middleware. When a developer starts `AgentOS`, a network attacker who…
- risk 0.59cvss —epss —
## Summary The `codeMode` tool in `src/praisonai-ts/src/tools/builtins/code-mode.ts` uses `new Function()` with a `with(sandbox)` pattern to execute LLM-generated code. The blocklist-based "sandbox" can be trivially bypassed via `Function('return this')()` to recover the global…
- risk 0.59cvss —epss —
# Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands ## Summary PraisonAI 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…
- risk 0.59cvss —epss —
# PraisonAI `AgentTeam.launch()` exposes unauthenticated remote agent invocation endpoints ## Summary PraisonAI's documented Python `AgentTeam.launch()` / `Agents.launch()` HTTP server starts externally reachable agent invocation endpoints without any authentication…
- risk 0.59cvss —epss —
# 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…
- risk 0.59cvss —epss —
# 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:**…
- risk 0.59cvss —epss —
# 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…
- risk 0.57cvss 9.8epss 0.00
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an insecure default cryptographic key. The JWT signing secret defaults to the hardcoded literal `"dev-secret-change-me"` when `PLATFORM_JWT_SECRET` is unset. A…
- risk 0.57cvss 9.8epss 0.00
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by…
- risk 0.57cvss 9.8epss 0.00
PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented…
- risk 0.57cvss 9.9epss 0.01
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution…
- risk 0.57cvss 9.8epss 0.00
PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the table_prefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization.…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run <file.yaml> loads a YAML file with…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags (such as !!js/function and !!js/undefined). This allows an attacker to craft a malicious YAML file…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop,…
- risk 0.57cvss 9.8epss 0.01
PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the get_all_user_threads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via update_thread. When the application…
Page 1 of 6