Authorization Flaw in praisonai (CVE-2026-56074)
Summary
Vulnerability in praisonai (CVE-2026-56074). Confidential information can be exposed externally. Exploitable via execute_command. Mitigation: upgrade to 4.5.128 or later.
Original description
The description as published by the source.
Summary
The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves execute_command for any command (e.g., ls -la), all subsequent execute_command calls in that execution context bypass the approval prompt entirely. Combined with os.environ.copy() passing all process environment variables to subprocesses, this allows an LLM agent (potentially via prompt injection) to silently exfiltrate API keys and credentials without further user consent.
Details
The require_approval decorator in src/praisonai-agents/praisonaiagents/approval/__init__.py:176-178 checks approval status by tool name only:
@wraps(func)
def wrapper(*args, **kwargs):
if is_already_approved(tool_name): # line 177 — checks only tool_name
return func(*args, **kwargs) # line 178 — bypasses ALL approval
The mark_approved function in registry.py:144-147 stores only the tool name string:
def mark_approved(self, tool_name: str) -> None:
approved = self._approved_context.get(set())
approved.add(tool_name) # stores "execute_command", not args
self._approved_context.set(approved)
The approval context is never cleared during agent execution — clear_approved() exists (registry.py:152) but is never called in the agent's tool execution path (agent/tool_execution.py).
Meanwhile, the ConsoleBackend UI at backends.py:95-96 misleads the user:…
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-56074 has been found in praisonai.
Attackers can target a specific entry point like execute_command over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: 5.5/10.
What to do: upgrade praisonai to 4.5.128 or later.
If unsure, ask your IT team or search "praisonai CVE-2026-56074" on the vendor's site.
CVE-2026-56074 (praisonai) — CWE-863 / CVSS v3 5.5
Attack vector: local / unauthenticated
Attack surface: execute_command / require_approval / mark_approved / ConsoleBackend
Patched: 4.5.128 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Incorrect authorization (CWE-863) exists in praisonai. Attackers reach the vulnerable code path via execute_command without authentication.
Check the vendor advisory for the affected versions of praisonai. Attack surface: execute_command / require_approval / mark_approved / ConsoleBackend.
Severity: Medium (CVSS 5.5/10). Confidential information can be exposed externally.
Update to 4.5.128.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'praisonai' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'praisonai' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
praisonaiを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade praisonai to 4.5.128ステージング環境で 4.5.128 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory nvd.nist.gov
- advisory github.com
- package github.com
- package pypi.org
- web github.com
- web vulncheck.com
- web github.com
- web github.com