mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-08-15 07:50:20 +02:00
Remove the best-supported/recommended framing from the README prerequisites and limitations, docs/safety.md, and docs/ai-providers.md. The remaining caveat is model-neutral: capability varies, and a model that does not follow Shannon's instructions or tool-use constraints reliably produces weaker pentests. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>