Loading story…
Multiple vulnerabilities in PraisonAI and praisonaiagents exposed deployments to unauthorized access and server-side request forgery. CVE-2026-55528 stems from AgentServer declaring an auth_token but not enforcing it on any route, allowing remote unauthenticated users to subscribe, publish, and invoke other actions even when authentication was configured. The issue affects PraisonAI versions earlier than 4.6.58 and praisonaiagents versions earlier than 1.6.58, and was rated high severity with impact to integrity.
Two SSRF flaws also affected the platform’s network-facing features. CVE-2026-55526 allowed crafted hostnames such as 127.0.0.1.nip.io to bypass hostname blocking because spider_tools._host_is_blocked() did not resolve hostnames before requests were made, enabling access to loopback and other internal resources. Separately, CVE-2026-55537 exposed webhook handling to a DNS race and fail-open validation bug: an authenticated attacker with job submission rights and control of authoritative DNS could register a webhook that initially failed resolution, then repoint it before delivery so the background executor sent HTTP POST requests to internal targets including 127.0.0.1 and 169.254.169.254. A hardening commit added authentication enforcement, DNS-based SSRF checks, and broader fail-closed validation, while fixes were released in updated PraisonAI and praisonaiagents versions.
Track how attackers are adapting to this technology.
9 events from the most recent confirmed update back to the earliest known activity.
CVE-2026-55539 was published for a high-severity missing-authentication flaw where PraisonAI versions before 4.6.51 exposed the Jobs API /api/v1/runs endpoint without authentication. Unauthenticated reachable callers could submit, read, cancel, or delete jobs under operator credentials; version 4.6.58 adds PRAISONAI_JOBS_API_KEY middleware and fixes the issue.
CVE-2026-55533 was published for a high-severity authentication-bypass flaw in PraisonAI's create_auth_middleware(), which can allow unauthenticated Recipe server requests when API-key or JWT authentication is configured but its required secret environment variable is absent. An externally exposed server could accept unauthenticated POST requests to /v1/recipes/run; PraisonAI 4.6.58 fixes the issue.
CVE-2026-55532 was published for a high-severity prefix-based origin-validation flaw in PraisonAI's MCP HTTP Stream component. An attacker-controlled origin such as localhost.attacker.com could bypass the localhost allowlist and invoke tools/call without an API key, including file-write actions; PraisonAI 4.6.58 fixes the issue.
CVE-2026-55525 was published for a high-severity SSRF flaw in praisonaiagents' web_crawl function, which did not revalidate redirect destinations followed by httpx. An attacker able to influence a crawl target could redirect requests to loopback, private-network, or cloud-metadata services and expose internal responses; version 1.6.58 remediates the issue.
CVE-2026-55535 was published for a medium-severity SSRF vulnerability in PraisonAI's Jobs API validate_webhook_url() logic, which fails open on socket.gaierror and does not bind the validated address to the subsequent request. The issue could allow attacker-controlled webhook URLs to reach localhost, cloud metadata endpoints, or other internal systems; PraisonAI 4.6.58 remediates it.
Security-advisories@github.com newly received CVE-2026-55526, describing an SSRF bypass in spider_tools._host_is_blocked() that allowed crafted hostnames such as 127.0.0.1.nip.io to resolve to loopback and enable internal HTTP access. The issue affected PraisonAI versions earlier than 4.6.58 and praisonaiagents versions earlier than 1.6.58.
Security-advisories@github.com newly received CVE-2026-55528, covering an authentication bypass in PraisonAI and praisonaiagents where AgentServer declared auth_token but did not enforce it on routes. The issue affected PraisonAI versions earlier than 4.6.58 and praisonaiagents versions earlier than 1.6.58.
CVE-2026-55524 was published for a high-severity SSRF flaw in praisonaiagents' web_crawl tool, which validated only the initial URL before following redirects or resolving the hostname again at connection time. An attacker controlling a processed URL could use redirects or DNS rebinding to access internal, loopback, private-network, or cloud metadata endpoints and receive their response bodies.
A public GitHub commit in the MervinPraison/PraisonAI repository introduced multiple security hardening changes, including enforcing AgentServer authentication, resolving spider hostnames with socket.getaddrinfo, and making jobs webhook validation fail closed on DNS resolution errors. The commit identifier was 2f9677abb2ea68eab864ee8b6a828fd0141612e1.
Vulnerabilities, threat actors, malware, products, organizations, breaches, and observables Mallory has linked to this story. Indicator values are masked here and available in full in the app.
Indicator values are masked on this page. See the values in Mallory Domains, IPs, hashes, and URLs are exportable to your SIEM.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
13 references tracked. Mallory keeps watching after this page renders.
cvefeed.io
Open sourcecvefeed.io
Open sourcecvereports.com
Open sourcetenable.com
Open sourcetenable.com
Open sourcegithub.com
Open sourcecwe.mitre.org
Open sourcecwe.mitre.org
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
PraisonAI, a multi-agent teams platform, disclosed two high-severity vulnerabilities affecting versions before **4.5.97** and **4.5.90**. The more severe issue, tracked as `CVE-2026-34953`, stems from `OAuthManager.validate_token()` returning `True` for tokens missing from its internal store, which is empty by default. That logic flaw lets attackers present arbitrary Bearer tokens to authenticate to the MCP server and gain full access to registered tools and agent capabilities. The vulnerability was classified as **CWE-863** with a CVSS v3.1 vector of `AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N`. A second flaw, `CVE-2026-34934`, exposed PraisonAI to second-order SQL injection through `get_all_user_threads`. In affected versions before **4.5.90**, the function constructed raw SQL queries with Python f-strings using unescaped thread IDs previously stored in the database, allowing an attacker to plant a malicious thread ID via `update_thread` and trigger injection when thread lists were loaded. The bug could lead to full database compromise and was classified as **CWE-89** with a CVSS v3.1 vector of `AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`; both issues were addressed in patched releases published through GitHub Security Advisories.
Jun 29, 2026
PraisonAI disclosed two high-severity vulnerabilities affecting its multi-agent teams platform, both tied to unsafe handling of templates. **CVE-2026-39891** affects versions before `4.5.115` and allows template injection through agent tool definitions: the `create_agent_centric_tools()` function returns tools that render file content as templates, so unescaped input supplied via `agent.start()` can cause template expressions to execute rather than be treated as plain text. The flaw is tracked as **CWE-94** and carries a CVSS v3.1 score vector of `AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H`, indicating high impact across confidentiality, integrity, and availability. A second issue, **CVE-2026-40154**, affects versions before `4.5.128` and exposes PraisonAI to remote template code execution through untrusted externally fetched template files. The advisory says the product treated remote templates as trusted executable code without integrity checks, origin validation, or user confirmation, creating a supply-chain attack path for malicious templates. That vulnerability is mapped to **CWE-829** with CVSS v3.1 vector `AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:N`. PraisonAI fixed the issues in versions `4.5.115` and `4.5.128`, with GitHub advisories published as **GHSA-hwg5-x759-7wjg** and **GHSA-pv9q-275h-rh7x**.
Jun 29, 2026
Threat actors began probing internet-exposed **PraisonAI** instances within **3 hours and 44 minutes** of public disclosure of `CVE-2026-44338`, a missing-authentication flaw in the product’s legacy Flask API server. The vulnerability, tracked in GitHub advisory `GHSA-6rmh-7xcm-cpxj`, affects versions **2.5.6 through 4.6.33** and was fixed in **4.6.34**. Sysdig said the issue stems from authentication being disabled by default in the legacy `api_server.py`, allowing unauthenticated access to protected endpoints including `GET /agents` and `POST /chat`. Sysdig observed scanning from **146.190.133[.]49** using the User-Agent **`CVE-Detector/1.0`**, with activity focused on validating exploitability rather than full hands-on abuse, as no `POST /chat` requests were seen. Even so, exposed deployments could allow attackers to view agent configurations, trigger workflows defined in `agents.yaml`, exhaust model or API quotas, expose data, or execute downstream actions through connected tools. Defenders were urged to upgrade to **PraisonAI 4.6.34 or later**, retire the legacy API server, restrict exposure of **port 8080**, monitor for unauthenticated requests to `/agents` and `/chat`, and review credentials and billing tied to configured agents.
Jun 29, 2026