Exploiting LLM APIs with Excessive Agency (PortSwigger Lab Write-up)

InfoSec Write-ups cybersecurity · April 11, 2026 · Original source

🚨 Lab: Exploiting LLM APIs with Excessive Agency (Apprentice)Continue reading on InfoSec Write-ups »

Related Vulnerabilities

CVE-2026-35649: OpenClaw before 2026.3.22 contains a settings reconciliation vulnerability that allows attackers to MEDIUM
CVE-2026-35670: OpenClaw before 2026.3.22 contains a webhook reply delivery vulnerability that allows attackers to r MEDIUM
CVE-2026-35647: OpenClaw before 2026.3.25 contains an access control vulnerability where verification notices bypass MEDIUM
CVE-2026-39922: GeoNode versions 4.0 before 4.4.5 and 5.0 before 5.0.2 contain a server-side request forgery vulnera N/A