CVE-2026-57118PYSEC-2026-3537GHSA-X8CV-XMQ7-P8XP
PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints
- Published
- Last modified
- Status
- published
- Known exploitation
- Not listed in CISA KEV
- Fix
- Fixed in 4.6.59, 1.6.59
- Public exploit
- None on Exploit-DB
CISA SSVC
- Exploitation: poc
- Automatable: yes
- Technical impact: total
?
Decision points from CISA's Vulnrichment, assessed (SSVC 2.0.3).
SSVC documentationSummary
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, AgentTeam.launch and the Agents alias register GET /{path}/list, POST /{path}, and `POST /{path}/{agent_id}' without access-control checks before listing agents or calling agent.chat. A remotely exposed server can therefore let unauthenticated clients enumerate agents, consume model resources, access connected private context, and trigger agent tools or workflow side effects. This vulnerability is fixed in praisonaiagents 1.6.59.
Affected versions
- MervinPraison PraisonAI
fixed in 4.6.59
- MervinPraison praisonaiagents
fixed in 1.6.59
- praisonaiagentsPyPI
fixed in 1.6.59