Vulnerabilities in pkg:pypi/PraisonAI

PACKAGE
Advisory Summary

GHSA-wrw8-384c-cg76 is a HIGH (CVSS 8.8) praisonai: shell command allowlist bypass vulnerability (CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')) affecting Duplicate Advisory libraries in the PyPI ecosystem. The issue involves praisonai: shell command allowlist bypass via find -exec built-in action. Remediation is available in the latest vendor maintenance releases.

54 Known Advisory Record(s)
Package Vulnerability Intelligence

pkg:pypi/PraisonAI

54 Known Advisory Record(s)

Vulnerability advisories affecting package pkg:pypi/PraisonAI. Select an advisory below to view technical details or fixes.

Advisory ID CVE / NVD Severity Summary
GHSA-wrw8-384c-cg76 - HIGH Duplicate Advisory: PraisonAI: Shell command allowlist bypass via find -exec built-in action
GHSA-65c8-r727-2mpj - HIGH Duplicate Advisory: PraisonAI: SecurityPolicy command/path/import restrictions are completely unenforced by the default SubprocessSandbox backend
GHSA-fj8f-m44g-c479 CVE-2026-61439 HIGH PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
GHSA-g6j7-pffp-8whg CVE-2026-62176 CRITICAL PraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generation
GHSA-6g6r-q6gw-w8fg CVE-2026-55536 CRITICAL PraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)
GHSA-pvph-5j39-v8qc CVE-2026-55532 HIGH PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server
GHSA-gfq8-hmph-9gjv CVE-2026-55533 HIGH PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret
GHSA-2jgc-f764-c5r2 CVE-2026-55539 HIGH PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete
GHSA-pvxx-r596-f5qj CVE-2026-55541 HIGH PraisonAI: `--api-key` flag on `praisonai serve` is not properly enforced
GHSA-hmfx-4v44-9qw9 CVE-2026-55535 MODERATE PraisonAI vulnerable to Server-Side Request Forgery via DNS rebinding bypass in webhook_url validation
GHSA-rg5q-pp8p-f7jm CVE-2026-55537 HIGH PraisonAI: Webhook SSRF via DNS fail-open in `JobSubmitRequest.validate_webhook_url()` — bypass of CVE-2026-40114
GHSA-r7v3-x45f-g7hp CVE-2026-55538 HIGH PraisonAI: [Auth Bypass] `praisonai serve agents --api-key` is silently ignored — agent-invocation routes (`POST /agents`, `POST /agents/{agent_name}`) run unauthenticated
GHSA-ch89-h4r2-c8f8 CVE-2026-55540 HIGH PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks
GHSA-7ww9-85pg-cv4x CVE-2026-55534 HIGH PraisonAI serve agents --api-key is ignored, allowing unauthenticated remote agent execution
GHSA-wv94-5qcp-6m36 CVE-2026-55531 MODERATE PraisonAI MCP HTTP server has unauthenticated unbounded session accumulation (memory exhaustion; session TTL never enforced)
GHSA-wj6g-v78p-6fx3 CVE-2026-55529 MODERATE PraisonAI has an origin validation bypass in MCP HTTP Stream transport that allows browser-mediated unauthenticated tool execution on local MCP server
GHSA-hxmv-c4g6-5fqc CVE-2026-55522 HIGH PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
GHSA-hvhp-v2gc-268q CVE-2026-47397 HIGH PraisonAI has an Arbitrary File Write in Python API
GHSA-vg22-4gmj-prxw CVE-2026-47391 CRITICAL PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution
GHSA-9cr9-25q5-8prj CVE-2026-47394 HIGH PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate
GHSA-4mr5-g6f9-cfrh CVE-2026-47392 CRITICAL PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
GHSA-5cxw-77wg-jrf3 CVE-2026-47395 MODERATE PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
GHSA-8444-4fhq-fxpq CVE-2026-47393 CRITICAL PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default
GHSA-86qc-r5v2-v6x6 CVE-2026-47396 CRITICAL PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset
GHSA-5c6w-wwfq-7qqm CVE-2026-47390 MODERATE PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings
GHSA-78r8-wwqv-r299 CVE-2026-47398 HIGH PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334
GHSA-9q28-ghcr-c4x3 CVE-2026-44340 HIGH PraisonAI's symlink-extraction bypass of `_safe_extractall` writes outside `dest_dir`
GHSA-gmjg-hv98-qggq CVE-2026-44339 HIGH PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
GHSA-9mqq-jqxf-grvw CVE-2026-44336 CRITICAL PraisonAI MCP `tools/call` path-traversal => RCE via Python `.pth` injection
GHSA-3643-7v76-5cj2 CVE-2026-44337 MODERATE PraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and CQL queries
GHSA-6rmh-7xcm-cpxj CVE-2026-44338 HIGH PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution
GHSA-x783-xp3g-mqhp CVE-2026-40315 MODERATE PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queries
GHSA-8x8f-54wf-vv92 CVE-2026-40289 CRITICAL PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessions
GHSA-vc46-vw85-3wvm CVE-2026-40288 CRITICAL PraisonAI has critical RCE via `type: job` workflow YAML
GHSA-g985-wjh9-qxxc CVE-2026-40287 HIGH PraisonAI Vulnerable to RCE via Automatic tools.py Import
GHSA-8frj-8q3m-xhgm CVE-2026-40114 HIGH PraisonAI Vulnerable to Server-Side Request Forgery via Unvalidated webhook_url in Jobs API
GHSA-pj2r-f9mw-vrcq CVE-2026-40159 MODERATE PraisonAI Vulnerable to Sensitive Environment Variable Exposure via Untrusted MCP Subprocess Execution
GHSA-99g3-w8gr-x37c CVE-2026-40157 CRITICAL PraisonAI vulnerable to arbitrary file write via path traversal in `praisonai recipe unpack`
GHSA-f2h6-7xfr-xm8w CVE-2026-40148 MODERATE PraisonAI Vulnerable to Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits
GHSA-pv9q-275h-rh7x CVE-2026-40154 CRITICAL PraisonAI Vulnerable Untrusted Remote Template Code Execution
GHSA-qwgj-rrpj-75xm - HIGH PraisonAI: Hardcoded `approval_mode="auto"` in Chainlit UI Overrides Administrator Configuration, Enabling Unapproved Shell Command Execution
GHSA-3c4r-6p77-xwr7 CVE-2026-40158 HIGH PraisonAI Vulnerable to Code Injection and Protection Mechanism Failure
GHSA-pm96-6xpr-978x CVE-2026-40151 MODERATE PraisonAI: Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS
GHSA-4wr3-f4p3-5wjh CVE-2026-40149 HIGH PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
GHSA-2xgv-5cv2-47vv CVE-2026-40115 MODERATE PraisonAI has Unrestricted Upload Size in WSGI Recipe Registry Server that Enables Memory Exhaustion DoS
GHSA-q5r4-47m9-5mc7 CVE-2026-40116 HIGH PraisonAI: Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without Rate Limits
GHSA-fvxx-ggmx-3cjg CVE-2026-40113 HIGH PraisonAI Vulnerable to Argument Injection into Cloud Run Environment Variables via Unsanitized Comma in gcloud --set-env-vars
GHSA-cfg2-mxfj-j6pw CVE-2026-40112 MODERATE PraisonAI Vulnerable to Stored XSS via Unsanitized Agent Output in HTML Rendering (nh3 Not a Required Dependency)
GHSA-2763-cj5r-c79m CVE-2026-40088 CRITICAL PraisonAI Vulnerable to OS Command Injection
GHSA-693f-pf34-72c5 CVE-2026-35615 CRITICAL PraisonAI Has Path Traversal in FileTools
GHSA-r9x3-wx45-2v7f CVE-2026-39308 HIGH PraisonAI recipe registry publish path traversal allows out-of-root file write
GHSA-4rx4-4r3x-6534 CVE-2026-39306 HIGH PraisonAI recipe registry pull path traversal writes files outside the chosen output directory
GHSA-jfxc-v5g9-38xr CVE-2026-39305 CRITICAL PraisonAI Vulnerable to Arbitrary File Write / Path Traversal in Action Orchestrator
GHSA-4ph2-f6pf-79wv CVE-2026-39307 HIGH PraisonAI Has Arbitrary File Write (Zip Slip) in Templates Extraction

GHSA-wrw8-384c-cg76 at a Glance

CVE Identifier N/A
GHSA Identifier GHSA-wrw8-384c-cg76
Severity HIGH
CVSS v3.1 Base Score 8.8
CWE Classification CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Affected Product Duplicate Advisory
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 8.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required Low (PR:L)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix GHSA-wrw8-384c-cg76

To remediate this vulnerability, upgrade all affected Duplicate Advisory dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

PraisonAI fixed: Latest secure release
pip install PraisonAI>=Latest secure release
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show PraisonAI

How to Check if You Are Affected

To determine whether your Python environment is affected by GHSA-wrw8-384c-cg76, inspect your installed packages using pip:

pip show PraisonAI

Analyze the terminal output to locate any version of Duplicate Advisory in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than the patched release), your application is affected.

Note: The pip show PraisonAI command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection'), where the product constructs all or part of an os command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended os command when it is sent to a downstream component. In Duplicate Advisory, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-cv3g-hj65-pcfh. This link is maintained to preserve external references. ### Original Description 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, delete files, or execute non-allowlisted binaries without triggering shell metacharacter filters.

GHSA-wrw8-384c-cg76 Affected Duplicate Advisory Versions

1 component(s)
Product / Package Ecosystem Affected Versions Fixed Version
PraisonAI
PyPI
≤ 4.6.77

References

Frequently Asked Questions

What is GHSA-wrw8-384c-cg76?
GHSA-wrw8-384c-cg76 is a security vulnerability in Duplicate Advisory involving PraisonAI: Shell command allowlist bypass via find -exec built-in action under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection').
Which Duplicate Advisory versions are affected?
Affected versions include releases prior to current release patches across affected packages: PraisonAI.
What version fixes GHSA-wrw8-384c-cg76?
Upgrading to current release patches (or the latest patched release for your respective branch) resolves the vulnerability.
Is PraisonAI affected?
Yes, PraisonAI is affected in releases prior to Latest secure release. Upgrade your dependency to Latest secure release or later.
What is the CVSS score of GHSA-wrw8-384c-cg76?
GHSA-wrw8-384c-cg76 has a CVSS v3.1 base score of 8.8 (HIGH) with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with GHSA-wrw8-384c-cg76?
GHSA-wrw8-384c-cg76 is classified under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') (The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.).
How can I check PyPI dependencies for GHSA-wrw8-384c-cg76?
Run the dependency tree command: 'pip show PraisonAI'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-wrw8-384c-cg76",
  "modified" : "2026-10-08T22:00:49Z",
  "published" : "2026-07-10T15:31:42Z",
  "withdrawn" : "2026-10-08T22:00:49Z",
  "aliases" : [ ],
  "summary" : "Duplicate Advisory: PraisonAI: Shell command allowlist bypass via find -exec built-in action",
  "details" : "### Duplicate Advisory\nThis advisory has been withdrawn because it is a duplicate of GHSA-cv3g-hj65-pcfh. This link is maintained to preserve external references.\n\n### Original Description\nPraisonAI 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, delete files, or execute non-allowlisted binaries without triggering shell metacharacter filters.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H"
  }, {
    "type" : "CVSS_V4",
    "score" : "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "PraisonAI"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "last_affected" : "4.6.77"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cv3g-hj65-pcfh"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-61434"
  }, {
    "type" : "WEB",
    "url" : "https://www.vulncheck.com/advisories/praisonai-before-allowlist-bypass-via-find-exec"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-78" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-10-08T22:00:49Z",
    "nvd_published_at" : "2026-07-10T15:16:50Z"
  }
}