# CVE-2026-56074: MervinPraison PraisonAI tool approval cache bypass in praisonaiagents

Source: https://junglewise.ai/threats/cve-2026-56074-mervinpraison-praisonai-tool-approval-cache-bypass-in  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-18. Updated: 2026-06-21  
License: CC BY 4.0 with a link back

CVE-2026-56074 · Severity: medium · CVSS 5.5 · Published 2026-06-18

PraisonAI, a framework for AI agents, contains a security flaw in how it handles user permission for running system commands. When a user approves a single safe command (like listing files), the system mistakenly remembers that approval for all future commands in that session. This allows an AI agent—potentially manipulated by a malicious prompt—to silently run dangerous commands to steal sensitive data like API keys and passwords without the user's knowledge.

Technologies: [MervinPraison PraisonAI Agents](https://junglewise.ai/threats/technologies/praisonai-agents), [praisonaiagents (PyPI)](https://junglewise.ai/threats/technologies/pypi-praisonaiagents). Vendors: [MervinPraison](https://junglewise.ai/threats/vendors/mervinpraison), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-56074 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-56074 being exploited in the wild.

**How severe is CVE-2026-56074?** Medium severity, with a CVSS score of 5.5, published 18 June 2026.

**Which products and versions are affected?** praisonaiagents (PyPI) ECOSYSTEM:introduced=0,fixed=4.5.128.

**Is there a fix for CVE-2026-56074?** Yes. praisonaiagents (PyPI): upgrade to 4.5.128 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-56074 attacked?** It is attacked with local access, in a software library.

**Am I affected by CVE-2026-56074?** Check whether you run MervinPraison PraisonAI Agents or praisonaiagents (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- praisonaiagents (PyPI): upgrade to 4.5.128 or later

  ```sh
  pip install "praisonaiagents>=4.5.128"
  ```


## Technical details

The vulnerability exists in the 'require_approval' decorator within the PraisonAI Agents approval system. The system caches approval status using only the tool name (e.g., 'execute_command') as the key, failing to include the specific invocation arguments in the cache lookup. Consequently, once a user provides manual consent for a benign command, all subsequent calls to that tool are automatically authorized for the remainder of the execution context. An attacker can leverage this via prompt injection to first request a harmless command and then silently execute shell commands to exfiltrate process environment variables (such as OPENAI_API_KEY) which are passed to subprocesses via 'os.environ.copy()'. The issue is addressed in version 1.5.128.

## Affected products

- MervinPraison PraisonAI (praisonaiagents) < 1.5.128

## Identifiers

- CVE-2026-56074
- GHSA-ffp3-3562-8cv3
- PYSEC-2026-2946

## Timeline

- 2026-04-09: advisory: GitHub Security Advisory published
- 2026-06-18: disclosed: NVD publication date

## References

- [https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-ffp3-3562-8cv3](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-ffp3-3562-8cv3)
- [https://www.vulncheck.com/advisories/praisonai-tool-approval-cache-bypass-via-coarse-grained-caching](https://www.vulncheck.com/advisories/praisonai-tool-approval-cache-bypass-via-coarse-grained-caching)

## Related threats

- [PraisonAI SearxNG URL validation bypass in search tools](https://junglewise.ai/threats/cve-2026-57143-praisonai-server-side-request-forgery-ssrf-in-searxng-search-web)
- [PraisonAI missing access control in API endpoints](https://junglewise.ai/threats/cve-2026-57118-praisonai-agentteam-launch-exposes-unauthenticated-remote-agent)
- [PraisonAI legacy SSE endpoint CORS and authentication bypass](https://junglewise.ai/threats/cve-2026-57112-praisonai-legacy-sse-endpoint-cors-and-authentication-bypass)
- [PraisonAI IMAP injection in email tools](https://junglewise.ai/threats/cve-2026-57130-praisonai-imap-injection-in-email-tools)
- [PraisonAI path traversal in file mention parsing](https://junglewise.ai/threats/cve-2026-57129-praisonai-path-traversal-in-file-mention-parsing)