Skip to content
OpenAdvisories

Product · Mervin Praison

PraisonAI

147 known vulnerabilities.

147 results · Feed

  • Medium 5.3
    CVE-2026-40151 Scanner template

    PraisonAI Affected by Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system instructions to any unauthenticated caller. The AgentOS…

  • High 7.9

    PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g.…

  • Medium 6.5

    PraisonAI Affected by Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the _safe_extractall() function in PraisonAI's recipe registry validates archive members against path traversal attacks but performs no checks on individual member sizes, cumulative extracted size, or…

  • High 7.5

    PraisonAI's Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without Rate Limits

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the /media-stream WebSocket endpoint in PraisonAI's call module accepts connections from any client without authentication or Twilio signature validation. Each connection opens an authenticated sessio…

  • Medium 6.2

    PraisonAI has an Unrestricted Upload Size in WSGI Recipe Registry Server Enables Memory Exhaustion DoS

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the WSGI-based recipe registry server (server.py) reads the entire HTTP request body into memory based on the client-supplied Content-Length header with no upper bound. Combined with authentication be…

  • High 7.2

    PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the /api/v1/runs endpoint accepts an arbitrary webhook_url in the request body with no URL validation. When a submitted job completes (success or failure), the server makes an HTTP POST request to thi…

  • High 8.4

    PraisonAI has an Argument Injection into Cloud Run Environment Variables via Unsanitized Comma in gcloud --set-env-vars

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, deploy.py constructs a single comma-delimited string for the gcloud run deploy --set-env-vars argument by directly interpolating openai_model, openai_key, and openai_base without validating that these…

  • Medium 5.4

    PraisonAI has Stored XSS via Unsanitized Agent Output in HTML Rendering (nh3 Not a Required Dependency)

    PraisonAI is a multi-agent teams system. Prior to 4.5.128, the Flask API endpoint in src/praisonai/api.py renders agent output as HTML without effective sanitization. The _sanitize_html function relies on the nh3 library, which is not listed as a required or …

  • Critical 9.7

    Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai

    PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitra…

  • High 8.8

    PraisonAI has a Template Injection in Agent Tool Definitions

    PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tool…

  • Critical 9.8

    PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading

    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 m…

  • High 7.5

    PraisonAI has Unauthenticated SSE Event Stream Exposes All Agent Activity in A2U Server

    PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication ch…

  • High 8.1

    PraisonAI has an Arbitrary File Write (Zip Slip) in Templates Extraction

    PraisonAI is a multi-agent teams system. Prior to 1.5.113, The PraisonAI templates installation feature is vulnerable to a "Zip Slip" Arbitrary File Write attack. When downloading and extracting template archives from external sources (e.g., GitHub), the appl…

  • High 7.1

    PraisonAI recipe registry publish path traversal allows out-of-root file write

    PraisonAI is a multi-agent teams system. Prior to 1.5.113, PraisonAI's recipe registry publish endpoint writes uploaded recipe bundles to a filesystem path derived from the bundle's internal manifest.json before it verifies that the manifest name and version …

  • High 7.3

    PraisonAI recipe registry pull path traversal writes files outside the chosen output directory

    PraisonAI is a multi-agent teams system. Prior to 1.5.113, PraisonAI's recipe registry pull flow extracts attacker-controlled .praison tar archives with tar.extractall() and does not validate archive member paths before extraction. A malicious publisher can u…

  • Critical 9.0

    Arbitrary File Write / Path Traversal in Action Orchestrator

    PraisonAI is a multi-agent teams system. Prior to 1.5.113, the Action Orchestrator feature contains a Path Traversal vulnerability that allows an attacker (or compromised agent) to write to arbitrary files outside of the configured workspace directory. By sup…

  • Critical 9.2

    PraisonAI has a Path Traversal in FileTools

    PraisonAI is a multi-agent teams system. Prior to 1.5.113, _validate_path() calls os.path.normpath() first, which collapses .. sequences, then checks for '..' in normalized. Since .. is already collapsed, the check always passes. This makes the check complete…

  • High 8.8

    PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox

    PraisonAI is a multi-agent teams system. Prior to version 4.5.97, SubprocessSandbox in all modes (BASIC, STRICT, NETWORK_ISOLATED) calls subprocess.run() with shell=True and relies solely on string-pattern matching to block dangerous commands. The blocklist d…

  • High 8.6

    PraisonAI: SSRF in FileTools.download_file() via Unvalidated URL

    PraisonAI is a multi-agent teams system. Prior to version 1.5.95, FileTools.download_file() in praisonaiagents validates the destination path but performs no validation on the url parameter, passing it directly to httpx.stream() with follow_redirects=True. An…

  • Critical 9.1

    PraisonAI: Authentication Bypass in OAuthManager.validate_token()

    PraisonAI is a multi-agent teams system. Prior to version 4.5.97, OAuthManager.validate_token() returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated…

  • Critical 9.1

    PraisonAI: Missing Authentication in WebSocket Gateway

    PraisonAI is a multi-agent teams system. Prior to version 4.5.97, the PraisonAI Gateway server accepts WebSocket connections at /ws and serves agent topology at /info with no authentication. Any network client can connect, enumerate registered agents, and sen…

  • Medium 6.5

    PraisonAI: ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

    PraisonAI is a multi-agent teams system. Prior to version 4.5.90, MCPToolIndex.search_tools() compiles a caller-supplied string directly as a Python regular expression with no validation, sanitization, or timeout. A crafted regex causes catastrophic backtrack…

  • Critical 10.0
    CVE-2026-34938 EPSS 13%

    PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

    PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to th…

  • High 7.8

    PraisonAI: Shell Injection in run_python() via Unescaped $() Substitution

    PraisonAI is a multi-agent teams system. Prior to version 1.5.90, run_python() in praisonai constructs a shell command string by interpolating user-controlled code into python3 -c "<code>" and passing it to subprocess.run(..., shell=True). The escaping logic …

  • High 7.7

    PraisonAI: SSRF via Unvalidated api_base in passthrough() Fallback

    PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough() and apassthrough() in praisonai accept a caller-controlled api_base parameter that is concatenated with endpoint and passed directly to httpx.Client.request() when the litellm pri…

  • Critical 9.8

    PraisonAI: Second-Order SQL Injection in `get_all_user_threads`

    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. Whe…

  • Critical 9.8

    PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

    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…