design docs agents

danielrmay/claudity

Agent

Deliberate misuse and attack by adversarial actors: who would attack, why, and how. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.

danielrmay/claudity

Agent

Human and AI error: user mistakes, operator misconfiguration, cognitive biases, information loss. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.

danielrmay/claudity

Agent

Security vulnerabilities: authentication, authorization, data protection, injection, cryptography, and supply chain. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.