Skip to content
OpenAdvisories

Product · Mervin Praison

PraisonAI

147 known vulnerabilities.

147 results · Feed

  • Medium 6.5

    PraisonAI: SpiderTools redirect-target SSRF protection bypass

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, SpiderTools.scrape_page validates only the initial URL and lets requests.Session.get follow redirects automatically, so a public-looking URL can redirect to a loopback, private, link-lo…

  • Critical 9.8

    PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @requi…

  • Critical 9.1

    Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, Browser Server _handle_connection() checks Chrome extension origins with re.match() and the unanchored expression chrome-extension://[a-z0-9]{32}. Extra trailing characters pass before websoc…

  • High 7.6

    PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can…

  • High 8.2

    PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. An externally bound Recipe server can therefore accept una…

  • High 8.6

    PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, the Jobs API create_app function mounts /api/v1/runs without authentication. Any reachable caller can submit jobs, read results, cancel runs, or delete jobs using operator credentials. The fi…

  • High 7.1

    PraisonAI: Arbitrary file write via unsanitized `user_id` in `FileMemory.__init__()` — path traversal to any writable location

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the FileMemory constructor joins unsanitized user_id into self.user_path. A caller supplying ../ or path separators can escape the memory directory and write JSON data to arbitrary proc…

  • High 8.8

    PraisonAI: `--api-key` flag on `praisonai serve` is not properly enforced

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve unified parse --api-key but _create_agents_app() and _create_unified_app() do not install a credential check. Unauthenticated callers can reach POST…

  • Medium 6.8

    PraisonAI: Server-Side Request Forgery via DNS rebinding bypass in webhook_url validation

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the Jobs API validate_webhook_url() path fails open on socket.gaierror and does not bind the validated address to the later request. An attacker webhook_url can later resolve to 127.0.0.1, 16…

  • High 7.1

    PraisonAI: Webhook SSRF via DNS fail-open in `JobSubmitRequest.validate_webhook_url()` — bypass of CVE-2026-40114

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validate_webhook_url() accepts webhook_url when resolution raises socket.gaierror because the exception path uses except socket.gaierror: pass. JobExecutor._send_webhook() la…

  • High 7.3

    PraisonAI: [Auth Bypass] `praisonai serve agents --api-key` is silently ignored — agent-invocation routes (`POST /agents`, `POST /agents/{agent_name}`) run unauthenticated

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, praisonai serve agents parses config["api_key"] but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. Missing or incorrect bearer and X-API-Key values stil…

  • High 7.1

    PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, is_path_within_directory() uses os.path.abspath() rather than os.path.realpath() for the workspace boundary. A symlink inside workspace can point outside and still pass the check, allowing re…

  • Medium 6.1

    PraisonAI: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, ast_grep_rewrite lacks the @require_approval decorator used by sibling mutation tools. With dry_run=False, an agent-controlled call can pass --update-all and a broad path to rewrite mat…

  • High 8.6

    PraisonAI serve agents --api-key is ignored, allowing unauthenticated remote agent execution

    PraisonAI is a multi-agent teams system. From praisonai 4.6.34 until 4.6.58, praisonai serve agents accepts --api-key but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. A network caller can invoke configured agents witho…

  • High 8.5

    PraisonAI: SSRF protection bypass in `spider_tools._host_is_blocked()` via DNS-resolved hostnames (`127.0.0.1.nip.io`)

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, spider_tools._host_is_blocked() does not resolve ordinary hostnames before scrape_page fetches them. A hostname such as 127.0.0.1.nip.io passes validation and resolves to loopback, perm…

  • Medium 6.5

    PraisonAI: Unauthenticated unbounded session accumulation in the PraisonAI MCP HTTP server (memory exhaustion; session TTL never enforced)

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcp_post handler creates a new _sessions entry for every initialize request but does not call _cleanup_sessions or enforce a maximum. An unauthenticated caller can exhaust…

  • High 8.2

    praisonaiagents: AgentServer declares auth_token but never enforces it on any route (CWE-862)

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, AgentServer exposes ServerConfig.auth_token but AgentServer._create_app does not check it on any route. A remote caller can subscribe, publish, and perform other actions without a valid…

  • Medium 6.9

    PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without …

  • High 7.5

    PraisonAI: SSRF via redirect-following in praisonaiagents web_crawl

    PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the web_crawl function validates only the initial URL before _crawl_with_httpx uses httpx.Client(follow_redirects=True). Redirect targets are not revalidated, so an attacker who influen…

  • High 7.5

    PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)

    PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The chec…

  • High 7.7

    PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets

    PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback …

  • High 7.8

    PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code

    PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an…

  • Critical 10.0

    PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name

    PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or val…

  • High 8.1

    PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334

    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 cal…

  • High 7.1

    PraisonAI has an Arbitrary File Write in Python API

    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 producti…

  • Critical 9.8

    PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

    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` …

  • Medium 5.5

    PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

    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 prom…

  • High 8.7

    PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate

    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(s…

  • Critical 9.8

    PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

    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 fo…

  • Critical 9.9

    PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

    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 `prin…

  • Critical 9.8

    PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

    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…

  • Medium 5.5

    PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings

    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 functi…

  • High 8.4

    PraisonAI before 1.6.78 Remote Code Execution via Plugin Auto-Discovery

    PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py) files from project-level and user-home .praisonai/plugins/ directories using importlib spec_from_fi…

  • High 8.1

    PraisonAI before 1.6.78 Remote Code Execution via SkillTools

    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 locati…

  • High 7.3

    PraisonAI before 4.6.78 Remote Code Execution via Broken AST Sandbox

    PraisonAI before 4.6.78 contains a remote code execution vulnerability in JobWorkflowExecutor._exec_inline_python() due to insufficient AST validation of workflow script steps. Attackers can create malicious YAML workflow files with import os statements follo…

  • Medium 6.5

    PraisonAI Platform before 0.1.9 Authorization Bypass via Label Endpoints

    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 exploi…

  • High 8.6

    PraisonAI before 4.6.78 Missing Webhook Signature Verification

    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 a…

  • High 8.2

    PraisonAI before 4.6.78 Authentication Bypass via Host Header Spoofing

    PraisonAI before 4.6.78 contains an authentication bypass in the Call API agent invocation endpoints (src/praisonai/praisonai/api/agent_invoke.py) when PRAISONAI_CALL_AUTH=disabled is configured. The safeguard intended to restrict the disabled-auth opt-out to…

  • High 7.8

    PraisonAI before 4.6.78 Code Injection via API deployment generator

    PraisonAI before 4.6.78 fails to safely encode deployment configuration values when generating Python source code for API servers. Attackers can inject arbitrary Python expressions through the deploy.api.host and agents_file configuration parameters that exec…

  • High 8.5

    PraisonAI before 1.6.78 DNS Rebinding SSRF via web_crawl

    PraisonAI before 1.6.78 contains a server-side request forgery vulnerability in the web_crawl tool that validates hostnames at check time but re-resolves them at connection time without IP pinning. Attackers can use DNS rebinding to bypass SSRF protection and…