CVE-2026-55522 PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code

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. Workflow.executeinclude implicitly imports and runs an included recipe's tools.py via a raw...

CVE-2026-55522 PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code

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. Workflow.executeinclude implicitly imports and runs an included recipe's tools.py via a raw...

CVE-2026-48168

PraxionAI’s multi-agent PraisonAI system is affected by a command-injection in the bundled Claude GitHub Actions workflow prior to version 4.6.40. The vulnerability arises from an attacker-controllable pull request branch name injected into an unquoted Bash run block, combined with triggering by ...

CVE-2026-48168 PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow...

CVE-2026-48168

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow...

CVE-2026-48168 PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow...

CVE-2026-55522: Improper Control of Generation of Code

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. Workflow.executeinclude implicitly imports and runs an included recipe's tools.py via a raw...

CVE-2026-48168: Missing Authorization

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow...

PT-2026-68315

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.6.58 Description The web crawl tool contains a Server-Side Request Forgery SSRF flaw. The system performs a security check on the initial URL by resolving the hostname via socket.gethostbyname to reject private,...

PT-2026-68308

Name of the Vulnerable Software and Affected Versions PraisonAI versions 1.5.128 through 1.6.57 Description The web crawl function in praisonaiagents.tools.web crawl tools is susceptible to server-side request forgery SSRF. Although the system validates the initial URL to block direct loopback an...

PT-2026-68307

Name of the Vulnerable Software and Affected Versions praisonai versions 3.9.26 through 4.6.57 praisonaiagents versions 0.12.12 through 1.6.57 Description The workflow include feature allows for arbitrary Python code execution. The Workflow. execute include function implicitly imports and runs a...

CVE-2026-55524: Time-of-check Time-of-use (TOCTOU) Race Condition

PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the webcrawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with...

CVE-2026-55523: Server-Side Request Forgery (SSRF)

PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.webcrawltools.webcrawl function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback and private destinations, its default httpx...

PT-2026-68302

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.40 Description The bundled Claude GitHub Actions workflow is susceptible to command injection. This occurs because the workflow embeds a pull request branch name into a Bash run: block without proper quoting or...

PraisonAI - Authentication Bypass Detection

PraisonAI 2.5.6 to 4.6.34 contains a broken authentication caused by disabled default authentication in legacy Flask API server, letting remote attackers access /agents and trigger workflows without token, exploit requires network access to API server. !/usr/bin/env python3 -- coding: utf-8 --...

Remote Code Execution

PraisonAI is vulnerable to Remote Code Execution RCE. The vulnerability is due to loading and executing plugin files without code signing, integrity verification, or sandboxing, allowing attackers to place malicious Python plugins in trusted plugin directories and execute arbitrary code when the...

PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

SummaryThe multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user inp...

PYSEC-2026-3500 PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints

PraisonAI AgentTeam.launch exposes unauthenticated remote agent invocation endpoints SummaryPraisonAI's documented Python AgentTeam.launch / Agents.launch HTTP server starts externally reachable agent invocation endpoints without any authentication enforcement.The current implementation registers...

PYSEC-2026-3512 PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...