CVE-2026-61447GHSA-2XV2-W8CQ-5GXWPYSEC-2026-4266
PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 1.6.78
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- 1 on Exploit-DB
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: poc
- Automatable: yes
- Technical impact: total
Summary
PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: poc · Automatable: yes · Technical impact: total
- Record last updated
- Public exploit on Exploit-DB
EDB-52639
- EPSS reached 10%
FIRST estimates at least a 10% chance of exploitation in the next 30 days
Affected versions
- MervinPraison PraisonAI
fixed in 1.6.78
- praisonaiagentsPyPI
fixed in 1.6.78