| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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 retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix. |
| 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 remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue. |
| PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue. |
| 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 quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input — LLM orchestration with the API key materials present in the process environment, and does not require any authentication. Versions prior to 4.6.40 still ship the generator with `auth_enabled` defaulting to `False`. The fix shape is opt-in via `APIConfig(auth_enabled=True, auth_token=...)`. Version 4.6.40 fixes the issue. |
| 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 `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. Version 4.6.40 fixes the issue. |
| PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, parse numeric IPv4 variants, or validate the final resolved IP address before making the request. As a result, certain URLs may bypass the protection and still reach loopback services. After the weak validation passes, `scrape_page()` calls `requests.Session.get()` on the attacker-controlled URL. This allows an attacker who can influence URLs passed to `scrape_page`, `crawl`, or `extract_text` to induce SSRF requests against loopback-only services. This is a server-side request forgery protection bypass. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a patch. |
| PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params["arguments"]` with no enforcement against the tool's declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix. |
| PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature checking, or the env-var gate. Version 4.6.40 fixes the issue. |
| PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix. |
| PraisonAI Platform before 0.1.9 fails to properly authorize label and issue-label mutations, allowing workspace members to rename and recolor shared labels and add or remove labels on owner-created issues. Attackers with workspace member privileges can exploit PATCH and POST/DELETE endpoints to alter shared label taxonomy and manipulate issue-label associations without owner or admin authorization. |
| PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream' without an API key, an unauthenticated client (no Authorization header, and no Origin header, which is also permitted) can initialize a session, enumerate the available tools (tools/list), and invoke tools (tools/call). Additionally, the dispatcher forwards tool-call arguments to handlers without validating them against the advertised inputSchema. The server binds to 127.0.0.1 by default, so remote exploitation requires the operator to bind to a network-accessible address (e.g., --host 0.0.0.0). |
| PraisonAI before 4.6.78 fails to verify Svix webhook signatures in AgentMail webhook mode, allowing unauthenticated attackers to forge message.received events. Attackers can send crafted JSON payloads to the webhook endpoint to invoke configured agents with arbitrary sender addresses and message content. |
| PraisonAI before 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial approvals for subsequent calls with arbitrary arguments. Attackers can exploit this by obtaining approval for a benign operation and then executing dangerous file write operations with unreviewed parameters in the same session. |
| PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run_skill_script() that executes scripts without path containment validation. Attackers can supply absolute file paths to execute arbitrary scripts from any filesystem location, including those outside the intended working directory. |
| PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store create_collection() backends. Although schema, keyspace, and collection-name identifiers are validated, the dimension value (declared as int but not enforced at runtime) is interpolated directly into the vector column of the generated CREATE TABLE DDL. A caller able to influence collection-creation dimensions can pass a string such as '3); DROP TABLE tenant_secrets; --' to inject SQL/CQL tokens into the statement executed by the database driver. |
| PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem locations and execute arbitrary shell commands with root privileges. |
| PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonai-agents/praisonaiagents/workflows/workflows.py). When a workflow step uses a string output_pydantic reference, the framework locates and imports a sibling tools.py from the workflow file's directory via importlib exec_module without sandboxing, ignoring the PRAISONAI_ALLOW_*_TOOLS environment variables. An attacker who controls a workflow file and its sibling tools.py can execute arbitrary Python code with the workflow runner's privileges when the workflow is executed via WorkflowManager or after load_yaml. |
| PraisonAI Platform (praisonai-platform) before 0.1.9 fails to enforce owner/admin authorization on the PATCH routes for projects, issues, and agents, which only require workspace-member role. A workspace member can modify owner-created records; for projects, a member can reassign lead_id to their own user id and then delete the owner-created project, bypassing the delete route's owner/admin permission check. |
| PraisonAI versions before 1.6.78 contain a server-side request forgery vulnerability in the Crawl4AI/Chromium backend that allows attackers to bypass SSRF validation by exploiting DNS rebinding and HTTP redirects. Attackers can craft URLs that resolve to internal services after the initial validation check, enabling the headless browser to follow redirects and read internal responses including sensitive canary values. |
| PraisonAI versions before 4.6.78 contain an allowlist bypass vulnerability in shell command execution that allows attackers to execute restricted commands via find's built-in -exec, -execdir, and -delete actions. Attackers can craft find commands with these built-in actions to read blocked files, delete files, or execute non-allowlisted binaries without triggering shell metacharacter filters. |
