Patch Forecast
Yellow warning
Plan into this sprint.

CVE-2026-60088 · GHSA-xpx6-x8c2-mw5w

PraisonAI: Project custom command templates can read outside-workspace files into model prompts

Risk score
40/100
CVSS
5.5 v3.1
Exploit chance (30 days)
0.2%
Published
11 Jul 2026

Open in the live forecast Today's forecast

What to know

What it is
PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model promp…
Affected
praisonai (pip) <= 4.6.77
Fix
Upgrade praisonai to 4.6.78 or later.
Exploitation
No known exploitation

Story map

Story map: praisonaiTHE FLAWSTHE FIXCVE-2026-60088PraisonAI: Project customcommand templates can readoutside-workspace files into…CVSS 5.5 · EPSS 0%CVE-2026-61445PraisonAI: AICoder ArbitraryFile Write and CommandExecution via LLM Tool CallsCVSS 9.9 · EPSS 1%CVE-2026-61426PraisonAI: AgentOS defaults tonetwork-exposed no-authmode, allowing…CVSS 8.6 · EPSS 0%CVE-2026-61434PraisonAI: Shell commandallowlist bypass via find -execbuilt-in actionCVSS 8.8 · EPSS 1%Upgrade praisonai4.6.78 · 1.7.3or later on your release lineWho is exposedpraisonai (pip) <= 4.6.77AMBER · PATCH THIS WEEKpraisonaiPraisonAI before 4.6.78contains arbitrary file write andcommand executionvulnerabilities in the AICodercomponent due to missing pathvalidation and commandsanitization in LLM tool calls.…Where it standsPublic proof of conceptCONNECTS TOSame weaknessPath traversal (CWE-22)398 other warnings in 30 days →
Story map: the flaws, the fix, how it unfolded and what it connects to. Boxes link to the record or article.

At a glance

praisonai: Amber, patch this week. PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem locations and execute …

The flaws

  • CVE-2026-60088: PraisonAI: Project custom command templates can read outside-workspace files into model prompts (CVSS 5.5 · EPSS 0%)
  • CVE-2026-61445: PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls (CVSS 9.9 · EPSS 1%)
  • CVE-2026-61426: PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent invocation and instruction disclosure (CVSS 8.6 · EPSS 0%)
  • CVE-2026-61434: PraisonAI: Shell command allowlist bypass via find -exec built-in action (CVSS 8.8 · EPSS 1%)

The fix

Upgrade praisonai: 4.6.78 · 1.7.3 or later on your release line

Who is exposed: praisonai (pip) <= 4.6.77

Where it stands

  • Public proof of concept

Connects to

Why it is Yellow

  • CVSS 5.5 medium
  • On your watchlist: PyPI

Affected packages

PackageEcosystemVulnerableFixed in
praisonaipip<= 4.6.774.6.78

References

Original description

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model prompts.

Last activity 8 Oct 2026. Patch Forecast updates every hour.