CVE-2026-61439 PraisonAI before 4.6.78 Prompt Injection Defense Bypass

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financi...

CVE-2026-61429 PraisonAI before 1.6.78 SSRF via Crawl4AI Chromium backend

PraisonAI versions before 1.6.78 contain a server-side request forgery vulnerability in the Crawl4AI/Chromium backend that allows attackers to bypass SSRF validation by exploiting DNS rebinding and HTTP redirects. Attackers can craft URLs that resolve to internal services after the initial...

CVE-2026-61429 PraisonAI before 1.6.78 SSRF via Crawl4AI Chromium backend

PraisonAI versions before 1.6.78 contain a server-side request forgery vulnerability in the Crawl4AI/Chromium backend that allows attackers to bypass SSRF validation by exploiting DNS rebinding and HTTP redirects. Attackers can craft URLs that resolve to internal services after the initial...

CVE-2026-61429

CVE-2026-61429 affects PraisonAI before 1.6.78. A SSRF in the Crawl4AI/Chromium backend allows bypassing initial validation via DNS rebinding and HTTP redirects, enabling a headless browser to access internal services and read internal responses including sensitive canary values. The CVSS metrics...

CVE-2026-61428 PraisonAI AgentMail before 4.6.78 Message Injection via Webhook

PraisonAI AgentMail versions before 4.6.78 lack signature verification in webhook mode, allowing unauthenticated attackers to inject messages with spoofed sender addresses. Attackers can POST crafted message.received events to the webhook endpoint to inject arbitrary content into the agent and...

CVE-2026-61428 PraisonAI AgentMail before 4.6.78 Message Injection via Webhook

PraisonAI AgentMail versions before 4.6.78 lack signature verification in webhook mode, allowing unauthenticated attackers to inject messages with spoofed sender addresses. Attackers can POST crafted message.received events to the webhook endpoint to inject arbitrary content into the agent and...

CVE-2026-61426

PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated attackers can call GET /api/agents to read agent instructions and system prompts, or POST /api/chat to invoke agents without authentication...

CVE-2026-61426 PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults

PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated attackers can call GET /api/agents to read agent instructions and system prompts, or POST /api/chat to invoke agents without authentication...

CVE-2026-61426 PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults

PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated attackers can call GET /api/agents to read agent instructions and system prompts, or POST /api/chat to invoke agents without authentication...

CVE-2026-60090 PraisonAI before 4.6.78 SQL/CQL Injection via vector dimension

PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store createcollection backends. Although schema, keyspace, and collection-name identifiers are validated, the dimension value declared as int but not enforced at runtime is...

CVE-2026-60090

CVE-2026-60090 affects PraisonAI prior to 4.6.78, exposing a SQL/CQL injection risk via the vector dimension in the PGVector and Cassandra knowledge-store backends. The root cause is that the caller-controlled dimension value is interpolated into the generated CREATE TABLE DDL without runtime enf...

CVE-2026-60090 PraisonAI before 4.6.78 SQL/CQL Injection via vector dimension

PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store createcollection backends. Although schema, keyspace, and collection-name identifiers are validated, the dimension value declared as int but not enforced at runtime is...

CVE-2026-60088

CVE-2026-60088 affects PraisonAI prior to 4.6.78. The issue is a path traversal flaw in custom command templates, where file paths are not validated, allowing an attacker to read files outside the workspace (e.g., @../outside_secret.txt or absolute paths) and exfiltrate process-readable files int...

CVE-2026-60088 PraisonAI before 4.6.78 Path Traversal via Custom Commands

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outsidesecret.txt or absolute paths in project command files to exfiltrate process-readable...

CVE-2026-60088

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outsidesecret.txt or absolute paths in project command files to exfiltrate process-readable...

CVE-2026-60088 PraisonAI before 4.6.78 Path Traversal via Custom Commands

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outsidesecret.txt or absolute paths in project command files to exfiltrate process-readable...

CVE-2026-61429: Server-Side Request Forgery (SSRF)

PraisonAI versions before 1.6.78 contain a server-side request forgery vulnerability in the Crawl4AI/Chromium backend that allows attackers to bypass SSRF validation by exploiting DNS rebinding and HTTP redirects. Attackers can craft URLs that resolve to internal services after the initial...

CVE-2026-61445: Improper Limitation of a Pathname to a Restricted Directory

PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem...

CVE-2026-61428: Authentication Bypass by Spoofing

PraisonAI AgentMail versions before 4.6.78 lack signature verification in webhook mode, allowing unauthenticated attackers to inject messages with spoofed sender addresses. Attackers can POST crafted message.received events to the webhook endpoint to inject arbitrary content into the agent and...

CVE-2026-61447: Improper Control of Generation of Code

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...