THREAT OPS › Threat News › [GHSA] GHSA-fj8f-m44g-c479 (high) — PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
[GHSA] GHSA-fj8f-m44g-c479 (high) — PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
GHSA-fj8f-m44g-c479 Severity: high CVE: CVE-2026-61439
PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
### Summary Injection Defense is a purpose-built prompt injection defense layer. It scans LLM inputs through six detection categories: instruction overrides, authority claims, boundary manipulation, obfuscation, financial manipulation, and self-harm instructions.
The defens
MITRE ATT&CK techniques
- System PromptAML.T0069.002
Indicators of compromise
- CVE-2026-61439cve
Original source: https://github.com/advisories/GHSA-fj8f-m44g-c479