CVE-2026-61437

CVE-2026-61437 : PraisonAI (pip package praisonaiagents) prior to 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow.resolve_pydantic_class. When a workflow step uses a string output_pydantic reference, the framework imports a sibling tools.py from the workflow directory ...

CVE-2026-61441

PraisonAI Platform before version 0.1.9 suffers an authorization bypass in the DELETE dependency endpoint: the route validates permissions against the caller-selected URL issue but allows deletion via a member-owned issue endpoint if the dependency edge is related to a member, bypassing owner/adm...

EUVD-2026-42899

PraisonAI versions before 4.6.78 contain an allowlist bypass vulnerability in shell command execution that allows attackers to execute restricted commands via find's built-in -exec, -execdir, and -delete actions. Attackers can craft find commands with these built-in actions to read blocked files,...

CVE-2026-61434

CVE-2026-61434 involves PraisonAI prior to version 4.6.78, where an allowlist bypass in shell command execution enables attackers to abuse find’s built-in -exec, -execdir, and -delete actions. By crafting find commands that use these actions, an attacker can read blocked files, delete files, or r...

CVE-2026-61434 PraisonAI before 4.6.78 Allowlist Bypass via find -exec

PraisonAI versions before 4.6.78 contain an allowlist bypass vulnerability in shell command execution that allows attackers to execute restricted commands via find's built-in -exec, -execdir, and -delete actions. Attackers can craft find commands with these built-in actions to read blocked files,...

EUVD-2026-42898

PraisonAI praisonaiagents before 1.6.78 contains a path traversal vulnerability in the FastContext feature praisonaiagents.context.fast. FastContextAgent.executetool prepends the configured workspacepath only for relative paths and neither rejects absolute paths nor canonicalizes joined paths...

EUVD-2026-42897

PraisonAI before 4.6.78 contains a path traversal vulnerability in ContextGatherer that fails to validate include paths in .praisoncontext and .praisoninclude files. Attackers can supply absolute paths or parent directory traversal sequences to read arbitrary files outside the workspace and inclu...

CVE-2026-61432

PraisionAI (praisonaiagents) before 1.6.78 has a path traversal flaw in the FastContext feature. FastContextAgent.execute_tool() only prefixes workspace_path for relative paths and does not reject absolute paths or canonicalize joined paths, allowing tool arguments or model-generated calls to gre...

CVE-2026-61431 PraisonAI before 4.6.78 Path Traversal via ContextGatherer

PraisonAI before 4.6.78 contains a path traversal vulnerability in ContextGatherer that fails to validate include paths in .praisoncontext and .praisoninclude files. Attackers can supply absolute paths or parent directory traversal sequences to read arbitrary files outside the workspace and inclu...

CVE-2026-61431 PraisonAI before 4.6.78 Path Traversal via ContextGatherer

PraisonAI before 4.6.78 contains a path traversal vulnerability in ContextGatherer that fails to validate include paths in .praisoncontext and .praisoninclude files. Attackers can supply absolute paths or parent directory traversal sequences to read arbitrary files outside the workspace and inclu...

CVE-2026-61431

PraxionAI (note: the spelling in the record appears as PraisonAI) before version 4.6.78 exposes a path traversal vulnerability in the ContextGatherer. The flaw stems from failing to validate include paths in .praisoncontext and .praisoninclude files, allowing an attacker with local access to supp...

CVE-2026-61432 PraisonAI FastContext before 1.6.78 Path Traversal

PraisonAI praisonaiagents before 1.6.78 contains a path traversal vulnerability in the FastContext feature praisonaiagents.context.fast. FastContextAgent.executetool prepends the configured workspacepath only for relative paths and neither rejects absolute paths nor canonicalizes joined paths...

CVE-2026-60091 PraisonAI before 4.6.78 Unauthenticated SSRF via webhook_url

PraisonAI before 4.6.78 contains an unauthenticated server-side request forgery vulnerability in the Jobs API /api/v1/runs endpoint. The webhookurl parameter is validated at request time but re-resolved at connection time, allowing attackers to use DNS rebinding to reach internal services with a...

CVE-2026-60091

PraisionAI before 4.6.78 is affected by an unauthenticated SSRF in the Jobs API /api/v1/runs. The webhook_url parameter is validated at request time but re-resolved at connection time, enabling DNS rebinding to reach internal services via a blind SSRF attack. CVSS metrics: CVSSv3.1 base score 7.2...

EUVD-2026-42896

PraisonAI before 4.6.78 contains an unauthenticated server-side request forgery vulnerability in the Jobs API /api/v1/runs endpoint. The webhookurl parameter is validated at request time but re-resolved at connection time, allowing attackers to use DNS rebinding to reach internal services with a...

CVE-2026-60091 PraisonAI before 4.6.78 Unauthenticated SSRF via webhook_url

PraisonAI before 4.6.78 contains an unauthenticated server-side request forgery vulnerability in the Jobs API /api/v1/runs endpoint. The webhookurl parameter is validated at request time but re-resolved at connection time, allowing attackers to use DNS rebinding to reach internal services with a...

CVE-2026-60086

PraisonAI before 4.6.78 contains a prompt injection defense bypass. The defense only blocks threats classified as CRITICAL and requires three or more detector families to match. Attackers can craft single- or double-vector prompt injections rated HIGH that pass through unblocked to reach the mode...

CVE-2026-60089

Prais onAI (pip package praisonaiagents) prior to version 1.6.78 is affected by a path-traversal issue: defaults loaded from a project-local .praisonai/config.toml can set defaults.output.output_file to an absolute or .. traversal path. If an Agent is started without an explicit output parameter,...

CVE-2026-60086 PraisonAI before 4.6.78 Prompt Injection Defense Bypass

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are...

CVE-2026-60089 PraisonAI before 1.6.78 Path Traversal via config.toml

PraisonAI pip package praisonaiagents before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.outputfile path. A repository-controlled config file can set outputfile to an absolute or '..' travers...