PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queries

SummaryThe tableprefix configuration value is directly used to construct SQL table identifiers without validation.If an attacker controls this value, they can manipulate SQL query structure, leading to unauthorized data access e.g., reading internal SQLite tables such as sqlitemaster and tamperin...

PYSEC-2026-2925 PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queries

Summary The tableprefix configuration value is directly used to construct SQL table identifiers without validation. If an attacker controls this value, they can manipulate SQL query structure, leading to unauthorized data access e.g., reading internal SQLite tables such as sqlitemaster and...

K000162232: Spring AI vulnerability CVE-2026-41713

Security Advisory Description A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversati...

PraisonAI Vulnerable to Server-Side Request Forgery via Unvalidated webhook_url in Jobs API

SummaryThe /api/v1/runs endpoint accepts an arbitrary webhookurl in the request body with no URL validation. When a submitted job completes success or failure, the server makes an HTTP POST request to this URL using httpx.AsyncClient. An unauthenticated attacker can use this to make the server se...

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 | Summarywebcrawl's httpx fallback path passes user-supplied URLs directly to...

PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

SummaryThe approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves executecommand for any command e.g., ls -la, all subsequent executecommand calls in that execution context bypass the approval prompt entirely. Combin...

PYSEC-2026-2946 PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves executecommand for any command e.g., ls -la, all subsequent executecommand calls in that execution context bypass the approval prompt entirely...

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...

PYSEC-2026-2906 PraisonAI Vulnerable to Server-Side Request Forgery via Unvalidated webhook_url in Jobs API

Summary The /api/v1/runs endpoint accepts an arbitrary webhookurl in the request body with no URL validation. When a submitted job completes success or failure, the server makes an HTTP POST request to this URL using httpx.AsyncClient. An unauthenticated attacker can use this to make the server...

PYSEC-2026-2945 PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool

Summary The webcrawl function in praisonaiagents/tools/webcrawltools.py accepts arbitrary URLs from AI agents with zero validation. No scheme allowlisting, hostname/IP blocklisting, or private network checks are applied before fetching. This allows an attacker or prompt injection in crawled conte...

PraisonAI: Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS

SummaryThe 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 defaults...

PraisonAI has Unrestricted Upload Size in WSGI Recipe Registry Server that Enables Memory Exhaustion DoS

SummaryThe WSGI-based recipe registry server server.py reads the entire HTTP request body into memory based on the client-supplied Content-Length header with no upper bound. Combined with authentication being disabled by default no token configured, any local process can send arbitrarily large PO...

PYSEC-2026-2919 PraisonAI: Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS

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...

PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

SummaryThe gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, an attacker can cause the ExecApprovalManager to...

PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool

SummaryThe webcrawl function in praisonaiagents/tools/webcrawltools.py accepts arbitrary URLs from AI agents with zero validation. No scheme allowlisting, hostname/IP blocklisting, or private network checks are applied before fetching. This allows an attacker or prompt injection in crawled conten...

PYSEC-2026-2896 PraisonAI has Unrestricted Upload Size in WSGI Recipe Registry Server that Enables Memory Exhaustion DoS

Summary The WSGI-based recipe registry server server.py reads the entire HTTP request body into memory based on the client-supplied Content-Length header with no upper bound. Combined with authentication being disabled by default no token configured, any local process can send arbitrarily large...

PraisonAI Vulnerable to Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits

SummaryThe safeextractall function in PraisonAI's recipe registry validates archive members against path traversal attacks but performs no checks on individual member sizes, cumulative extracted size, or member count before calling tar.extractall. An attacker can publish a malicious recipe bundle...

PraisonAIAgents: Path Traversal via Unvalidated Glob Pattern in list_files Bypasses Workspace Boundary

SummaryThe listfiles tool in FileTools validates the directory parameter against workspace boundaries via validatepath, but passes the pattern parameter directly to Path.glob without any validation. Since Python's Path.glob supports .. path segments, an attacker can use relative path traversal in...

PYSEC-2026-2901 PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

Summary The gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, an attacker can cause the ExecApprovalManager to...

PYSEC-2026-2912 PraisonAI Vulnerable to Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits

Summary The safeextractall function in PraisonAI's recipe registry validates archive members against path traversal attacks but performs no checks on individual member sizes, cumulative extracted size, or member count before calling tar.extractall. An attacker can publish a malicious recipe bundl...