« Volver al listado

Praison

Praisonaiagents: vulnerabilidades y CVE

Praisonaiagents tiene 38 vulnerabilidades publicadas, 38 de ellas en los últimos 12 meses. 8 son críticas y 0 figuran en el catálogo de explotación activa de CISA.

CVE38
Últimos 12 meses38
Críticas8
Explotadas activamente0

Todas las vulnerabilidades en el catálogo →⭐ Seguir esta tecnología

Últimas vulnerabilidades

CVESeveridadEPSSExplotación activaPublicadaDescripción
CVE-2026-57112Alta (8.3)0.22%—15 sept 2026
PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts…
CVE-2026-57130Alta (8.1)0.46%—14 sept 2026
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/email_tools.py interpolates LLM-controlled from_addr, subject, and query values directly into quoted…
CVE-2026-57128Media (4.3)0.25%—14 sept 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,…
CVE-2026-57126Alta (8.5)0.38%—14 sept 2026
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, SpiderTools._validate_url calls _host_is_blocked, which checks literal host encodings but does not resolve DNS names before scrape_page, crawl,…
CVE-2026-57125Crítica (9.8)0.60%—14 sept 2026
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…
CVE-2026-57123Crítica (9.8)0.90%—14 sept 2026
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, ToolsMCPServer.run_sse and launch_tools_mcp_server bind to 0.0.0.0 and create /sse and /messages/ routes without invoking the available…
CVE-2026-57120Media (6.5)0.56%—14 sept 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…
CVE-2026-57115Media (6.5)0.43%—14 sept 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…
CVE-2026-57129Alta (7.5)0.53%—14 sept 2026
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, MentionsParser._process_file_mention accepts file-mention values and falls back from workspace-relative resolution to Path(file_path) without…
CVE-2026-55530Media (6.1)0.17%—25 ago 2026
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…
CVE-2026-55528Alta (8.2)0.49%—25 ago 2026
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,…
CVE-2026-55527Alta (7.1)0.48%—25 ago 2026
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…
CVE-2026-55526Alta (8.5)0.36%—25 ago 2026
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…
CVE-2026-55525Alta (7.5)0.51%—25 ago 2026
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…
CVE-2026-55523Alta (7.7)0.47%—5 ago 2026
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…
CVE-2026-55522Alta (7.8)0.22%—5 ago 2026
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.…
CVE-2026-47395Media (5.5)0.18%—21 jul 2026
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…
CVE-2026-47392Crítica (9.9)0.88%—21 jul 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…
CVE-2026-47390Media (5.5)0.18%—21 jul 2026
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.…
CVE-2026-61446Alta (8.6)0.33%—15 jul 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/…
CVE-2026-61437Alta (8.5)0.17%—10 jul 2026
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…
CVE-2026-61432Media (6.9)0.41%—10 jul 2026
PraisonAI (praisonaiagents) before 1.6.78 contains a path traversal vulnerability in the FastContext feature (praisonaiagents.context.fast). FastContextAgent.execute_tool() prepends the configured workspace_path only…
CVE-2026-60089Media (6.9)0.18%—10 jul 2026
PraisonAI (pip package praisonaiagents) before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.output_file path. A…
CVE-2026-44339Alta (8.6)0.43%—8 may 2026
PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and __main__ after it fails to match…
CVE-2026-44335Alta (7.7)0.57%—8 may 2026
PraisonAI is a multi-agent teams system. Prior to version 1.6.32, the URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. This issue has been patched in…
CVE-2026-41496Alta (8.1)0.41%—8 may 2026
PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.9 and praisonaiagents version 1.6.9, the fix for CVE-2026-40315 added input validation to SQLiteConversationStore only. Nine sibling backends —…
CVE-2026-40289Crítica (9.1)0.52%—14 abr 2026
PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the browser bridge (praisonai browser start) is vulnerable to unauthenticated remote session hijacking due…
CVE-2026-40288Crítica (9.8)0.92%—14 abr 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.…
CVE-2026-40287Alta (8.4)0.23%—14 abr 2026
PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components…
CVE-2026-40160Alta (7.1)0.40%—10 abr 2026
PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, web_crawl's httpx fallback path passes user-supplied URLs directly to httpx.AsyncClient.get() with follow_redirects=True and no host validation. An LLM…

🎯 Cómo se explota (técnicas ATT&CK)

  1. T1190 Exploit Public-Facing Application14
  2. T1059 Command and Scripting Interpreter12
  3. T1210 Exploitation of Remote Services6
  4. T1090 Proxy4
  5. T1203 Exploitation for Client Execution4
  6. T1005 Data from Local System3

Número de CVE de esta tecnología asignadas a cada técnica de explotación o de impacto principal.

Otros productos de Praison