Repello AI
a free scan you can run without a sales call, behind numbers nothing supports.
the free entry point is real and useful; the headline capability claims have no methodology, paper or benchmark behind them that we could find.
the recon scan is a genuine self-serve starting point in a category that mostly refuses to give you one, and the described coverage is relevant: prompt injection, jailbreaks against safety guardrails, data exfiltration through context windows and rag pipelines, excessive agent autonomy, tool abuse and api exploitation, and resource exhaustion. testing is black-box and model-agnostic across openai, gemini, anthropic, llama and hugging face, and claims multimodal and 100-plus language coverage.
the headline numbers are where it loses ground. 270-plus vulnerability types and 15 million evolving attack patterns are large, specific-sounding figures with no paper, benchmark, disclosure record or methodology behind them that we could locate. against adversa's named cve-style findings and garak's peer-reviewed paper, that's assertion rather than evidence.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- ai red-teaming tools
- pricing
- free scan available
- website
- repello.ai
the free entry point is real and useful; the headline capability claims have no methodology, paper or benchmark behind them that we could find.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.