David Vs Goliath Verifiable

Audit and harden tool-augmented AI agent systems against Tag-Along Attacks -- adversarial agent-to-agent jailbreaks that exploit legitimate tool privileges through conversation. Use when asked to 'red-team an agent system', 'audit agentic tool safety', 'design verifiable agent security tests', 'build a tag-along attack harness', 'harden an operator agent against privilege escalation', or 'evaluate agent-to-agent attack surfaces'.

ndpvt-web Updated 14 repo stars

File contents

ndpvt-web/arxiv-claude-skills commit cca9d8f547

Frequently asked questions

npx get-skill add ndpvt-web/david-vs-goliath-verifiable