CVE-2026-109440
HIGH 8.7LangAlpha 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.
Severe if exploited (CVSS 8.7), but no known exploitation and low modeled probability. Patch on a normal cadence.
Exploitation likelihood
0.6%chance of exploitation in 30 days · 48th percentile
Impact if exploited
8.7CVSS 4.0 · HIGH
- ConfidentialityHigh
- IntegrityHigh
- AvailabilityHigh
What an attacker needs
- ✓Access: Reachable over the network — no local access needed
- ✓Privileges: No account or privileges required
- ⚠User interaction: Succeeds with passive user activity
- ✓Complexity: No special conditions — reliably repeatable
- ✓Requirements: No special attack requirements
✓ lowers the bar for an attacker · ⚠ raises it
Proof of concept
No public PoC is currently catalogued.
Search for new PoCs
Search GitHub now — results may be empty or unverified.
Tracked sources are checked daily for recent CVEs, including PoCs published after the original disclosure. A later release appears after a tracked source lists it and a refresh succeeds.
Data snapshot:
Weakness (CWE)
- CWE-1427: Improper Neutralization of Input Used for LLM Prompting
CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
References and research data (JSON)
All CVSS metrics
- HIGH 8.7 v4.0 · CNA Primary
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - HIGH 8.8 v3.1 · CNA Primary
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - HIGH 8.7 v4.0 · NVD Secondary
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - HIGH 8.8 v3.1 · NVD Primary
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
References
Exploit-tagged references (not proof of a PoC)
- https://www.lasso.security/vulnerability-database/cve-2026-109440 CVE record · VulnCheck · Updated 2026-10-22T21:08:25.014Z
NVD · CVE-2026-109440 · Updated 2026-10-22T22:18:00.100
Advisories
- https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode CVE record · VulnCheck · Updated 2026-10-22T21:08:25.014Z
NVD · CVE-2026-109440 · Updated 2026-10-22T22:18:00.100 - https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-104680 EUVD · EUVD-2026-104680
Technical & other
- https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524 CVE record · VulnCheck · Updated 2026-10-22T21:08:25.014Z
NVD · CVE-2026-109440 · Updated 2026-10-22T22:18:00.100