PraisonAI vulnerabilities

CVE-2026-58653 Medium · 4.3 CWE-639 Jul 2, 2026

PraisonAI - Authorization Bypass via Unvalidated project_id in Issue Create/Update

PraisonAI before 0.1.7 fails to validate that project_id in issue create and update request bodies belongs to the URL workspace. An attacker can create issues referencing projects from other workspaces, causing cross-tenant data pollution in project statistics aggregation without workspace constraints.

CVE-2026-56078 High · 8.8 CWE-22 Jun 18, 2026

PraisonAI - Arbitrary File Read and Write via Path Traversal in MultiAgentMonitor

PraisonAI before 1.5.115 contains a path traversal vulnerability in MultiAgentMonitor that fails to sanitize agent IDs when building file paths. Attackers can include traversal sequences like ../ in agent IDs to read, write, or overwrite arbitrary files, enabling sensitive disclosure, denial of service, or code execution.

CVE-2026-56077 Medium · 6.5 CWE-668 Jun 18, 2026

PraisonAI - Information Disclosure via Shared MultiAgentLedger State

PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger instances and expose system prompts and conversation history between agents.

CVE-2026-56076 High · 8.1 CWE-942 Jun 18, 2026

PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: * headers, combined with Starlette's Content-Type-agnostic JSON parsing, enabling attackers to bypass CORS preflight checks via simple requests and exfiltrate sensitive agent responses including tool execution results and environment data.

CVE-2026-56075 High · 8.8 CWE-863 Jun 18, 2026

PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

CVE-2026-56074 Medium · 5.5 CWE-863 Jun 18, 2026

PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.