PraisonAI
by PraisonAI
Source repositories
CVEs (77)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-55532 | Hig | 0.42 | 7.6 | 0.00 | Aug 25, 2026 | 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 send Content-Type:… | ||
| CVE-2026-55524 | Hig | 0.42 | 7.5 | 0.00 | Aug 5, 2026 | 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 check resolves the… | ||
| CVE-2026-56077 | Med | 0.42 | 6.5 | 0.00 | Jun 18, 2026 | PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger… | ||
| CVE-2026-57120 | Med | 0.35 | 6.5 | 0.00 | Sep 14, 2026 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr.… | ||
| CVE-2026-57115 | Med | 0.35 | 6.5 | 0.00 | Sep 14, 2026 | 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-local, or metadata… | ||
| CVE-2026-47411 | Med | 0.35 | 6.5 | 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 authorization bypass enabling workspace metadata + settings tampering. The `PATCH /workspaces/{workspace_id}` endpoint is gated only by… | ||
| CVE-2026-56074 | Med | 0.29 | 5.5 | 0.00 | Jun 18, 2026 | PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate… | ||
| CVE-2026-57128 | Med | 0.21 | 4.3 | 0.00 | Sep 14, 2026 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the SSE server in src/praisonai-agents/praisonaiagents/server/server.py does not consult ServerConfig.auth_token before handling /publish, /events, or /info requests. A network client that can reach the… | ||
| CVE-2026-61446 | Hig | 0.00 | 8.4 | 0.00 | Jul 15, 2026 | 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_file_location() and… | ||
| CVE-2026-61443 | Hig | 0.00 | 8.1 | 0.01 | Jul 15, 2026 | 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… | ||
| CVE-2026-61440 | Med | 0.00 | 6.5 | 0.00 | Jul 15, 2026 | 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… | ||
| CVE-2026-61438 | Hig | 0.00 | 7.3 | 0.00 | Jul 15, 2026 | 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 followed by os.system()… | ||
| CVE-2026-61436 | Hig | 0.00 | 8.6 | 0.01 | Jul 15, 2026 | 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… | ||
| CVE-2026-61435 | Hig | 0.00 | 8.2 | 0.01 | Jul 15, 2026 | 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 localhost binding… | ||
| CVE-2026-61433 | Hig | 0.00 | 7.8 | 0.00 | Jul 15, 2026 | 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 execute when the… | ||
| CVE-2026-61430 | Hig | 0.00 | 8.5 | 0.00 | Jul 15, 2026 | 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 retrieve internal… | ||
| CVE-2026-61427 | Hig | 0.00 | 7.3 | 0.00 | Jul 15, 2026 | 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… | ||
| CVE-2026-60087 | Med | 0.00 | 6.1 | 0.00 | Jul 15, 2026 | 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… | ||
| CVE-2026-60085 | Hig | 0.00 | 7.5 | 0.00 | Jul 15, 2026 | PraisonAI before 4.6.78 contains an unenforced security policy vulnerability in the default Subprocess Sandbox backend where blocked_commands, blocked_paths, blocked_imports, allow_subprocess, and allow_file_write restrictions are completely ignored. Attackers can execute… | ||
| CVE-2026-61447 | Cri | 0.00 | 10.0 | 0.02 | Jul 11, 2026 | PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to… |
- risk 0.42cvss 7.6epss 0.00
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 send Content-Type:…
- risk 0.42cvss 7.5epss 0.00
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 check resolves the…
- risk 0.42cvss 6.5epss 0.00
PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger…
- risk 0.35cvss 6.5epss 0.00
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr.…
- risk 0.35cvss 6.5epss 0.00
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-local, or metadata…
- risk 0.35cvss 6.5epss 0.00
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an authorization bypass enabling workspace metadata + settings tampering. The `PATCH /workspaces/{workspace_id}` endpoint is gated only by…
- risk 0.29cvss 5.5epss 0.00
PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate…
- risk 0.21cvss 4.3epss 0.00
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the SSE server in src/praisonai-agents/praisonaiagents/server/server.py does not consult ServerConfig.auth_token before handling /publish, /events, or /info requests. A network client that can reach the…
- risk 0.00cvss 8.4epss 0.00
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_file_location() and…
- risk 0.00cvss 8.1epss 0.01
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…
- risk 0.00cvss 6.5epss 0.00
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…
- risk 0.00cvss 7.3epss 0.00
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 followed by os.system()…
- risk 0.00cvss 8.6epss 0.01
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…
- risk 0.00cvss 8.2epss 0.01
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 localhost binding…
- risk 0.00cvss 7.8epss 0.00
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 execute when the…
- risk 0.00cvss 8.5epss 0.00
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 retrieve internal…
- risk 0.00cvss 7.3epss 0.00
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…
- risk 0.00cvss 6.1epss 0.00
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…
- risk 0.00cvss 7.5epss 0.00
PraisonAI before 4.6.78 contains an unenforced security policy vulnerability in the default Subprocess Sandbox backend where blocked_commands, blocked_paths, blocked_imports, allow_subprocess, and allow_file_write restrictions are completely ignored. Attackers can execute…
- risk 0.00cvss 10.0epss 0.02
PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to…
Page 3 of 4