MervinPraison has 46 CVEs on record. Disclosure cadence is accelerating: 46 in the last 90 days against 0 in the 90 before. The busiest recent month was September 2026 with 28. The median CVSS is 8.6 (high), with 14 rated critical. None have a confirmed exploitation report. The dominant weakness classes are CWE-306 (13) and CWE-863 (12). Most affected products: PraisonAI (41), praisonaiagents (4), praisonai-platform (1).
CVEs per month
Last 12 months, by publish date
- Exploited share
- 0% vs 1% corpus
- Median CVSS
- 8.6
- Publish → KEV
- —
- Last 90 days
- 46 prev 0
Weakness classes
Products
- PraisonAI 41
- praisonaiagents 4
- praisonai-platform 1
Worst active — by depth score
CVE-2026-57116Critical· 9.8PraisonAI: AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation66CVE-2026-57148Critical· 9.8PraisonAI is a multi-agent teams system66CVE-2026-57147Critical· 9.8PraisonAI is a multi-agent teams system66CVE-2026-57139Critical· 9.8PraisonAI is a multi-agent teams system66CVE-2026-57131Critical· 9.8PraisonAI is a multi-agent teams system66
MervinPraison vulnerabilities
CVEs affecting MervinPraison, newest first. Open any entry for full detail, references, and exploit status.
46 CVEsRSS
CVE-2026-57122High· 8.6PraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.59, the WhatsApp and Linear bot webhook handlers verify HMAC signatures only when WHATSAPP_APP_SECRET or LINEAR_WEBHOOK_SECRET is configured and otherwise parse and dispatch unsigned …
CVE-2026-57123Critical· 9.8PraisonAI is a multi-agent teams system
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 SecurityConfig authenticati…
CVE-2026-57126High· 8.5PoCPraisonAI is a multi-agent teams system
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, extract_links, extr…
CVE-2026-57120Medium· 6.5PoCPraisonAI is a multi-agent teams system
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 att…
CVE-2026-57124Critical· 9.8PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to Stdi…
CVE-2026-57119High· 7.5PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.59, the unauthenticated Jobs API accepts an absolute or traversing agent_file path in POST /api/v1/runs and passes it to the job executor without a workspace allowlist or boundary che…
CVE-2026-57127Critical· 9.8PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.58, recipe serve installs APIKeyAuthMiddleware or JWTAuthMiddleware when an operator selects api-key or JWT authentication, but each middleware forwards requests when PRAISONAI_API_KE…
CVE-2026-56839High· 7.3PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.59, the CODE_TOOLS wrappers keep _workspace_root as None and pass workspace=None to read_file, search_replace, and apply_diff helpers that enforce path containment only for a truthy w…
CVE-2026-57131Critical· 9.8PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.create_app mounts praisonai.jobs.router.create_router under /api/v1/runs without authentication or per-job authorization. Network clients can submit attacker…
CVE-2026-57130High· 8.1PoCPraisonAI is a multi-agent teams system
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 IMAP SEARCH criteri…
CVE-2026-57132High· 8.2PoCPraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/invoke without CALL_SERVER_TOKEN authentication. Deployments that use the applica…
CVE-2026-57115Medium· 6.5PraisonAI is a multi-agent teams system
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 loop…
CVE-2026-57125Critical· 9.8PoCPraisonAI is a multi-agent teams system
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-…
CVE-2026-57128Medium· 4.3PoCPraisonAI is a multi-agent teams system
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 reques…
CVE-2026-57129High· 7.5PoCPraisonAI is a multi-agent teams system
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 traversal, symlink, o…
CVE-2026-57145Critical· 9.1PraisonAI is a multi-agent teams system
PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a…