Skip to content
Threat Feed

Vendor

PraisonAI

4 briefs RSS
high advisory

PraisonAI Unsafe Tool Resolution Vulnerability

PraisonAI resolves tool names against module globals and `__main__` after failing to match declared tools, allowing an attacker who can influence tool-call names to invoke unintended application callables, leading to potential unauthorized state changes and command execution.

PraisonAI +1 vulnerability code-execution ai-agent
2r 1t 1c
high advisory

PraisonAI Symlink Extraction Bypass Vulnerability

PraisonAI versions 2.7.2 through 4.6.35 are vulnerable to an arbitrary file write due to improper validation of symlinks during archive extraction, affecting `recipe pull`, `recipe publish`, and `recipe unpack` flows.

PraisonAI symlink arbitrary file write path traversal attack.persistence attack.privilege_escalation
2r 2t 1c
critical advisory

PraisonAI MCP Path Traversal to RCE via .pth Injection

PraisonAI's MCP server is vulnerable to path traversal leading to arbitrary code execution by writing a Python `.pth` file into the user's site-packages directory, triggered via poisoned LLM contexts or unauthenticated HTTP-stream transports due to unvalidated kwargs in the dispatcher and lack of containment checks in file-handling tools.

MCP path-traversal code-execution prompt-injection
3r 3t
high advisory

PraisonAI Legacy API Server Authentication Bypass (CVE-2026-44338)

PraisonAI ships a legacy Flask API server with authentication disabled by default, allowing any reachable caller to access `/agents` and trigger the configured `agents.yaml` workflow through `/chat` without providing a token (CVE-2026-44338).

PraisonAI authentication bypass API CVE-2026-44338
2r 1t 1c