CVE-2026-109440
LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote…
- Risk score
- 76/100
- CVSS
- 8.8 v3.1
- Exploit chance (30 days)
- 0.5%
- Published
- 20 Oct 2026
Open in the live forecast Today's forecast
What to know
- What it is
- LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python code. Attackers can run code in the workspace sandbox and exfiltrate vault secrets.
- Affected
- {'products': ['LangAlpha'], 'packages': [], 'versions': ['through 2026.09.07']}
- Fix
- Check the linked advisory for a fix, as none is provided
- Exploitation
- No known exploitation
Why it is Amber
- CVSS 8.8 high
- Remotely exploitable without logging in
- On your watchlist: python
References
- https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524
- https://www.lasso.security/vulnerability-database/cve-2026-109440
- https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode
Original description
LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attackers can run code in the workspace sandbox and exfiltrate vault secrets from _internal/.vault_secrets.json.
Last activity 20 Oct 2026. Patch Forecast updates every hour.