PYSEC-2026-2334 aiwaves-cn agents is vulnerable to resource consumption in the recall_relevant_memories_to_working_memory function

A weakness has been identified in aiwaves-cn agents up to e8c4e3c2d19739d3dff59e577d1c97090cc15f59. Affected by this issue is the function recallrelevantmemoriestoworkingmemory of the file core/cat/lookingglass/straycat.py of the component cheshirecatcore. This manipulation causes resource...

PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

SummaryPraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. DetailsThe vulnerable server is the shipped...

PYSEC-2026-2904 PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

Summary PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. Details The vulnerable server is the shippe...

PYSEC-2026-2645 MetaGPT has an eval injection in metagpt/strategy/tot.py

A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function generatethoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit is...

PYSEC-2026-2951 PraisonAIAgents: SSRF via unvalidated URL in `web_crawl` httpx fallback

| Field | Value | |---|---| | Severity | High | | Type | SSRF -- unvalidated URL in webcrawl httpx fallback allows internal network access | | Affected | src/praisonai-agents/praisonaiagents/tools/webcrawltools.py:133-180 | Summary webcrawl's httpx fallback path passes user-supplied URLs directly...

CVE-2026-4765

Self Cross-Site Scripting Self-XSS vulnerability in the RD Station Conversas chat feature. The vulnerability lies in the ‘name’ parameter of the initialisation process due to incorrect sanitisation of user-supplied input. Exploitation allows specially crafted JavaScript code to be injected, which...

CVE-2026-4765 Self Cross-Site Scripting (Self-XSS) in Tallos Chat by RD Station Conversas

Self Cross-Site Scripting Self-XSS vulnerability in the RD Station Conversas chat feature. The vulnerability lies in the ‘name’ parameter of the initialisation process due to incorrect sanitisation of user-supplied input. Exploitation allows specially crafted JavaScript code to be injected, which...

CVE-2026-4765

RD Station Conversas (also known as Tallos Chat) is affected by a Stored Cross-Site Scripting (XSS) vulnerability in the name parameter of the chat initialization process, caused by insufficient sanitisation of user-supplied input. The initial CVE classification describes it as Self-XSS with impa...

EUVD-2026-43337

Stored Cross-Site Scripting XSS vulnerability in the RD Station Conversas chat. The vulnerability resides in the ‘name’ parameter of the initialization process due to improper sanitization of user input. The vulnerability is not limited to self-exploitation: when a support agent joins the...

CVE-2026-4765 Self Cross-Site Scripting (Self-XSS) in Tallos Chat by RD Station Conversas

Self Cross-Site Scripting Self-XSS vulnerability in the RD Station Conversas chat feature. The vulnerability lies in the ‘name’ parameter of the initialisation process due to incorrect sanitisation of user-supplied input. Exploitation allows specially crafted JavaScript code to be injected, which...

PT-2026-59059

Summary Microsoft APM normalizes marketplace plugins by copying plugin components referenced in plugin.json into .apm/. The manifest fields agents, skills, commands, and hooks are attacker-controlled, but the implementation does not enforce that those paths remain inside the plugin directory. A...

PT-2026-59288

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xml fill of the file metagpt/actions/action node.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated...

PT-2026-59562

Summary PraisonAI Platform's workspace-scoped REST routes contain a systemic object-level authorization flaw that allows an authenticated user from one workspace to access, modify, and delete objects belonging to another workspace by supplying the victim object's global UUID. The affected pattern...

PT-2026-57803

Stored Cross-Site Scripting XSS vulnerability in the RD Station Conversas chat. The vulnerability resides in the ‘name’ parameter of the initialization process due to improper sanitization of user input. The vulnerability is not limited to self-exploitation: when a support agent joins the...

PT-2026-59553

Summary The AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system instructions to any unauthenticated caller. The AgentOS FastAPI application has no authentication middleware, no API key validation, and default...

PT-2026-59541

Summary PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. Details The vulnerable server is the shippe...

mcp-server

NotCVE MCP Server !notcve/mcp-server MCP serverhttps://gl...

Information Exposure

Overview praisonai is a PraisonAI TypeScript AI Agents Framework - Node.js, npm, and Javascript AI Agents Framework Affected versions of this package are vulnerable to Information Exposure due to insecure default configuration that binds to all interfaces without requiring an API key and allows...

CVE-2026-61442

PraisonAI Platform praisonai-platform before 0.1.9 fails to enforce owner/admin authorization on the PATCH routes for projects, issues, and agents, which only require workspace-member role. A workspace member can modify owner-created records; for projects, a member can reassign leadid to their ow...

CVE-2026-61442

PraisonAI Platform before 0.1.9 has an authorization bypass on PATCH routes for projects, issues, and agents, where workspace-members can modify owner-created records. Specifically, a member can reassign lead_id to their own user id and then delete the owner-created project, bypassing the delete ...