PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments
Modified: 10/15/2026
package
pkg:pypi/praisonaiagents
PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments
Modified: 10/15/2026
PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal
Modified: 7/23/2026
PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets
Modified: 10/15/2026
PraisonAI: Unauthenticated Event Injection via SSE `/publish` Endpoint
Modified: 7/23/2026
PraisonAI Has SSRF in FileTools.download_file() via Unvalidated URL
Modified: 7/13/2026
PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass
Modified: 7/23/2026
PraisonAI: Unsafe Dynamic Module Loading Leads to Arbitrary Code Execution via tools.py in AgentFlow
Modified: 10/15/2026
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
Modified: 6/29/2026
PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameter
Modified: 7/23/2026
PraisonAI: FastContext path resolution permits absolute and traversal reads outside the workspace
Modified: 10/15/2026
PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings
Modified: 7/13/2026
PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Modified: 7/13/2026
praisonaiagents web_crawl vulnerable to SSRF via redirect-following
Modified: 9/10/2026
PraisonAI: Crawl4AI/Chromium backend is also affected by the `web_crawl` SSRF validation bypass
Modified: 10/15/2026
PraisonAI: SpiderTools redirect-target SSRF protection bypass
Modified: 7/23/2026
PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code
Modified: 6/29/2026
PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling
Modified: 7/13/2026
praisonaiagents: AgentServer declares auth_token but never enforces it on any route
Modified: 9/10/2026
PraisonAIAgents: Path Traversal via Unvalidated Glob Pattern in list_files Bypasses Workspace Boundary
Modified: 7/13/2026
PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool
Modified: 7/13/2026
praisonaiagents has a `web_crawl` SSRF protection bypass via unchecked redirect targets
Modified: 9/10/2026
PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessions
Modified: 6/29/2026
PraisonAI: SkillTools Executes Scripts Without Path Containment Validation
Modified: 10/15/2026
PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters
Modified: 7/23/2026
praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool
Modified: 9/10/2026
PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands
Modified: 9/10/2026
PraisonAI Vulnerable to RCE via Automatic tools.py Import
Modified: 7/13/2026
PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
Modified: 7/13/2026
PraisonAIAgents: Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate
Modified: 7/13/2026
praisonaiagents vulnerable to arbitrary file write via unsanitized `user_id` in `FileMemory.__init__()` — path traversal to any writable location
Modified: 9/10/2026
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
Modified: 9/10/2026
PraisonAI: Plugin Auto-Discovery Executes Arbitrary Python Files Without Verification
Modified: 10/15/2026
PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder
Modified: 7/23/2026
PraisonAI has an SSRF bypass
Modified: 7/13/2026
PraisonAI has sandbox escape via exception frame traversal in `execute_code` (subprocess mode)
Modified: 6/29/2026
PraisonAI: DNS rebinding bypass in `web_crawl` SSRF protection allows internal response disclosure
Modified: 10/15/2026
PraisonAI: Project config can auto-save agent output outside the project root
Modified: 10/15/2026
PraisonAIAgents: SSRF via unvalidated URL in `web_crawl` httpx fallback
Modified: 7/13/2026
PraisonAI: SQL Injection via unvalidated `table_prefix` in 9 conversation store backends (incomplete fix for CVE-2026-40315)
Modified: 7/13/2026
PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)
Modified: 6/29/2026
PraisonAIAgents: Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell Tool
Modified: 7/13/2026
PraisonAI has critical RCE via `type: job` workflow YAML
Modified: 6/29/2026
praisonaiagents vulnerable to SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)
Modified: 9/10/2026
PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools
Modified: 7/23/2026
praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS
Modified: 7/23/2026
PraisonAI: Shell Injection in run_python() via Unescaped $() Substitution
Modified: 7/13/2026
PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired in
Modified: 7/23/2026
praisonaiagents has an SSRF protection bypass in `spider_tools._host_is_blocked()` via DNS-resolved hostnames (`127.0.0.1.nip.io`)
Modified: 9/10/2026
PraisonAI: Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint
Modified: 9/10/2026
PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints
Modified: 7/23/2026
PraisonAI Has SSRF in FileTools.download_file() via Unvalidated URL
Modified: 7/13/2026
PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings
Modified: 7/13/2026
PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Modified: 7/13/2026
PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling
Modified: 7/13/2026
PraisonAIAgents: Path Traversal via Unvalidated Glob Pattern in list_files Bypasses Workspace Boundary
Modified: 7/13/2026
PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool
Modified: 7/13/2026
PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands
Modified: 10/23/2026
PraisonAI Vulnerable to RCE via Automatic tools.py Import
Modified: 7/13/2026
PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
Modified: 7/13/2026
PraisonAIAgents: Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate
Modified: 7/13/2026
PraisonAI has an SSRF bypass
Modified: 7/13/2026
PraisonAIAgents: SSRF via unvalidated URL in `web_crawl` httpx fallback
Modified: 7/13/2026
PraisonAI: SQL Injection via unvalidated `table_prefix` in 9 conversation store backends (incomplete fix for CVE-2026-40315)
Modified: 7/13/2026
PraisonAIAgents: Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell Tool
Modified: 7/13/2026
PraisonAI: Shell Injection in run_python() via Unescaped $() Substitution
Modified: 7/13/2026
PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal
Modified: 7/23/2026
PraisonAI: Unauthenticated Event Injection via SSE `/publish` Endpoint
Modified: 7/23/2026
PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass
Modified: 7/23/2026
PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameter
Modified: 7/23/2026
PraisonAI: SpiderTools redirect-target SSRF protection bypass
Modified: 7/23/2026
PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters
Modified: 7/23/2026
PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder
Modified: 7/23/2026
PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools
Modified: 7/23/2026
praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS
Modified: 7/23/2026
PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired in
Modified: 7/23/2026
PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints
Modified: 7/23/2026
praisonaiagents web_crawl vulnerable to SSRF via redirect-following
Modified: 9/10/2026
praisonaiagents: AgentServer declares auth_token but never enforces it on any route
Modified: 9/10/2026
praisonaiagents has a `web_crawl` SSRF protection bypass via unchecked redirect targets
Modified: 9/10/2026
praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool
Modified: 9/10/2026
praisonaiagents vulnerable to arbitrary file write via unsanitized `user_id` in `FileMemory.__init__()` — path traversal to any writable location
Modified: 9/10/2026
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
Modified: 9/10/2026
praisonaiagents vulnerable to SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)
Modified: 9/10/2026
praisonaiagents has an SSRF protection bypass in `spider_tools._host_is_blocked()` via DNS-resolved hostnames (`127.0.0.1.nip.io`)
Modified: 9/10/2026
PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments
Modified: 10/15/2026
PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets
Modified: 10/15/2026
PraisonAI: Unsafe Dynamic Module Loading Leads to Arbitrary Code Execution via tools.py in AgentFlow
Modified: 10/15/2026
PraisonAI: FastContext path resolution permits absolute and traversal reads outside the workspace
Modified: 10/15/2026
PraisonAI: Crawl4AI/Chromium backend is also affected by the `web_crawl` SSRF validation bypass
Modified: 10/15/2026
PraisonAI: SkillTools Executes Scripts Without Path Containment Validation
Modified: 10/15/2026
PraisonAI: Plugin Auto-Discovery Executes Arbitrary Python Files Without Verification
Modified: 10/15/2026
PraisonAI: DNS rebinding bypass in `web_crawl` SSRF protection allows internal response disclosure
Modified: 10/15/2026
PraisonAI: Project config can auto-save agent output outside the project root
Modified: 10/15/2026
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
Modified: 7/13/2026
PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code
Modified: 7/13/2026
PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessions
Modified: 7/13/2026
PraisonAI has sandbox escape via exception frame traversal in `execute_code` (subprocess mode)
Modified: 7/13/2026
PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)
Modified: 7/13/2026
PraisonAI has critical RCE via `type: job` workflow YAML
Modified: 7/13/2026