Results for “system-prompt-leakage”

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Elevate from a low-privilege user account to root access on a compromised Linux system by exploiting misconfigurations, vulnerable services, kernel exploits, and weak permissions.

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Exploits the MS17-010 (EternalBlue) vulnerability in Microsoft's SMBv1 implementation for authorized security testing, red team exercises, and penetration testing engagements.

Enumerate SMB, WinRM, LDAP, and MSSQL services, validate credentials, spray passwords, and execute commands on remote hosts using NetExec during authorized penetration tests.

Exploit privileged pods, host mounts, runC CVEs, and exposed Docker sockets to break out of a container and reach the underlying host during authorized container-security assessments.

Exploit path normalization discrepancies between CDN caching layers and origin servers to cache and retrieve authenticated content.

Simulates BGP hijacking attacks in isolated lab environments to test RPKI deployment, route origin validation, and BGP monitoring defenses against prefix hijacking and route leak attacks.