Remote Code Execution

PraisonAI is vulnerable to Remote Code Execution RCE. The vulnerability is due to missing path containment validation in SkillTools.runskillscript, where attacker-supplied absolute file paths are executed without restriction, allowing attackers to execute arbitrary scripts from any location on th...

EUVD-2026-46282

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, executecode in praisonaiagents/tools/pythontools.py v1.6.37, subprocess sandbox mode can be fully bypassed using print.self to retrieve the real Python builtins modul...

Arbitrary Code Injection

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

PT-2026-60142

PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run skill script that executes scripts without path containment validation. Attackers can supply absolute file paths to execute arbitrary scripts from any filesystem location, including those outside the intended...

PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Summarypraisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attack...

PYSEC-2026-2947 PraisonAI Vulnerable to RCE via Automatic tools.py Import

PraisonAI automatically imports ./tools.py from the current working directory when launching certain components. This includes call.py, toolresolver.py, and CLI tool-loading paths. A malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code...

CVE-2026-60090 PraisonAI before 4.6.78 SQL/CQL Injection via vector dimension

PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store createcollection backends. Although schema, keyspace, and collection-name identifiers are validated, the dimension value declared as int but not enforced at runtime is...

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...

PYSEC-2026-470 PraisonAI Has Second-Order SQL Injection in `get_all_user_threads`

Summary The getalluserthreads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via updatethread. When the application loads the thread list, the injected payload executes and grants full database...

GHSA-X44P-GG67-52FC Duplicate Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-ffp3-3562-8cv3. This link is maintained to preserve external references. Original Description PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing...

CVE-2026-56075

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

Protection Mechanism Failure

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 Protection Mechanism Failure via the codeMode process. An attacker can execute arbitrary code with the privileges of the host...

Missing Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

PraisonAI has an Arbitrary File Write in Python API

Bug Report: Arbitrary File Write in Python API Summary Hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. writefile skips path validation when workspace=None always None in production. Affected PraisonAI outputfile: /tmp/flag.txt...

Missing Authentication for Critical Function

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

PT-2026-45056

Name of the Vulnerable Software and Affected Versions PraisonAI versions 4.6.37 and earlier Description Hidden metadata within a webpage can trick PraisonAI agents into writing attacker-controlled content to arbitrary file paths. This occurs because the write file function skips path validation...

CVE-2026-44335

CVE-2026-44335 concerns PraisonAI prior to 1.6.32 with an SSRF bypass in the URL validation logic. The vulnerability arises from a discrepancy between Python urlparse() parsing and the requests library when handling certain URLs (e.g., http://127.0.0.1:[email protected]). urlparse() may extract a publ...

CVE-2026-40313

Summary: PraisonAI versions ≤ 4.5.139 expose GitHub Actions credential leakage via ArtiPACKED attack due to actions/checkout persisting GITHUB_TOKEN (and sometimes ACTIONS_RUNTIME_TOKEN) in the repository’s .git/config when artifacts are uploaded from workflows. This can allow read-access users t...

CVE-2026-40288

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run loads a YAML file with type: job, the...

EUVD-2026-22207

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py importtoolsfromfile, toolresolver.py loadlocaltools, and CLI...