GHSA-7p8g-6c6g-h9w7: praisonai-platform: Agent endpoints accept any agent_id without workspace ownership check, cross-workspace read/update/delete IDOR

Summary

The agent CRUD endpoints in praisonai-platform (GET, PATCH and DELETE on /workspaces/{workspace_id}/agents/{agent_id}) check only that the caller belongs to the workspace in the URL. AgentService.get resolves agent_id by primary key with no workspace_id predicate, so a member of one workspace can read, modify or delete agents in another workspace by supplying that agent's UUID. The flaw is an Insecure Direct Object Reference, tracked as GHSA-7p8g-6c6g-h9w7.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Related items

• MediumCVE-2026-122160: myshell-ai AIlice HuggingFace Model Wrapper untrusted model loadingSimilar attack · NVD/CVE Database
• MediumCVE-2026-122159: Edge0-AI Audio8_TTS path traversal via slow_decode_models argumentSimilar attack · NVD/CVE Database
• MediumCVE-2026-122235: Jan workspace guard bypass allows file writes outside workspace via symlinksSimilar attack · NVD/CVE Database
• HighCVE-2026-122135: Mistral Vibe remote code execution via repository gpg.program settingSimilar attack · NVD/CVE Database
• HighCVE-2026-122134: Mistral Vibe remote code execution through malicious Git filter driversSimilar attack · NVD/CVE Database