Vulnerabilities

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.

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.

PraisonAI AgentMail versions before 4.6.78 lack signature verification in webhook mode, allowing unauthenticated attackers to inject messages with spoofed sender addresses.

PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store create_collection() backends.

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace.