Prompt Injection Red-Team Harness
$2.99OfficialUse to adversarially test an LLM app, agent, or tool pipeline for prompt-injection/jailbreak weakness and produce a scored hardening report.
What you get
- ✓9-step procedure
- ✓Runnable Python included
- ✓8-point quality checklist
- ✓7 pitfalls to avoid
- ✓Installs into 6 tools
- Version
- v1 →
- Last updated
- today
- Length
- 8 min read
- Requires
- Best with a strong model (Claude Opus 5)
Works in: Claude Code, Codex, Cline, opencode, OpenClaw, Hermes · Built for large codebases
Preview
When to use
Invoke when you must adversarially test an LLM app, agent, or tool-using pipeline for prompt-injection and jailbreak weakness and produce a scored hardening report. Triggers: a target endpoint plus a security gate before release, a red-team engagement, a post-incident regression, or a request to measure Attack Success Rate (ASR) against known payload classes. Do NOT use for benign quality eval, latency/cost benchmarking, or fine-tuning data curation — those need different harnesses.
Assume you have written authorization to test the target. If scope is unclear, stop and confirm before sending a single adversarial request.
Inputs to gather
- Target interface: HTTP end
…
🔒 Buy once ($2.99) to unlock the full playbook, download it, and install it in every tool you use.