MediumVulnerabilityLLM-specific
CVE-2026-60086: PraisonAI prompt injection defense bypass via single or double-vector injections
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-60086
- Published
- Record updated
- Affected
- praisonai <= 4.6.77
- Fixed in
- 4.6.78
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
CVE-2026-60086 affects PraisonAI before 4.6.78. Its prompt injection defense only blocks threats classified as CRITICAL, which requires three or more detector families to match at once. Single or double-vector prompt injections rated HIGH pass through unblocked and reach the model.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- InfoTop GenAI security resources — October 2026Similar attack · Adversa AI Blog
- MediumGitLab patches a max-severity regex flaw alongside five high-severity bugsSimilar attack · CSO Online
- HighCVE-2026-96893: GitLab EE prompt injection into AI agent instructions via conversation contextSimilar attack · NVD/CVE Database
- HighCVE-2026-109331: Network-AI security control bypass in ClaudeHookBridge PreToolUse hookSimilar attack · NVD/CVE Database
- InfoIntroducing AI Coding Agent Governance: Using Hooks to Bring Visibility to the ADLC | Endor LabsSimilar attack · Endor Labs Blog