bastionprobe is an open-source CLI for sending indirect prompt-injection payloads to AI agents and reporting which attacks succeed. It is intended for developers and security researchers testing agent defenses.
bastionprobe sits in PulseGate's Penetration testing & red teaming category. It focuses on testing whether AI agents are vulnerable to indirect prompt-injection attacks. bastionprobe is an open-source project aimed at AI security researchers and developers of AI agents. The project is open source (MIT). bastionprobe is available on the command line, and it can be self-hosted.
Behind bastionprobe is Rinkia, and it first shipped in 2026. Development happens publicly on GitHub with 12 commits in the last 90 days. Among its 5 catalogued features are prompt injection testing, payload firing, and agent pentesting.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do