CVE-2026-57118: PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
• EPSS 0.3%, percentile 24: FIRST’s model estimates a 0.3% chance of exploitation activity in the next 30 days, higher than 24% of all scored CVEs (low). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes praisonaiagents (PyPI) < 1.6.59, fixed in 1.6.59. Check your lockfile, including transitive dependencies.

What it is

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}/{agentid}' 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.

From the GitHub advisory

PraisonAI AgentTeam.launch() exposes unauthenticated remote agent invocation endpoints

Summary

PraisonAI's documented Python AgentTeam.launch() / Agents.launch() HTTP server starts externally reachable agent invocation endpoints without any authentication enforcement.

The current implementation registers GET /{path}/list, POST /{path}, and POST /{path}/{agentid} routes. The POST routes directly call agent.chat(...). Requests with no Authorization header are accepted, and requests with an obviously wrong bearer token are also accepted. The default Python API bind host for Agents.launch() is 0.0.0.0, and official documentation shows host="0.0.0.0" for remote access.

This is a sibling/incomplete-fix variant of PraisonAI's prior unauthenticated API server and call server advisory family. Nearby server surfaces were hardened to require tokens, fail closed, or bind locally by default, but the AgentTeam.launch() FastAPI path still exposes unauthenticated agent execution on current upstream main and the latest release.

Weakness type: CWE-306, CWE-862.

Product: praisonaiagents (PyPI) · Assigned by: GitHub_M · Published: 2026-10-12

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Privileges required: none (no login)
• User interaction: none
• Scope: unchanged

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 0.33% probability of exploitation activity in the next 30 days; percentile 24.

Timeline

• 2026-06-18 — GitHub-reviewed advisory GHSA-x8cv-xmq7-p8xp published (critical)
• 2026-10-12 — CVE record published by GitHub_M
• 2026-10-15 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-x8cv-xmq7-p8xp github.com
2. CVE.org record CVE-2026-57118 cve.org
3. NVD entry CVE-2026-57118 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com

Critical PyPI advisories · Today’s Security Digest