Agent Abuse Pentest

Authorized testing of AI-agent + tool misuse paths for an MCP system. Covers direct and indirect prompt injection (via docs/issues/PRs/READMEs/tool results/resources/prompt templates), poisoned tool and parameter descriptions, client metadata poisoning, unconfirmed dangerous tool calls, secret exfiltration attempts, context/memory poisoning, cross-tenant mixups, and multi-server trust propagation. Safe-by-default; benign markers only; never triggers real destruction. Use when assessing how injected content can become tool misuse.

rwcod Updated

File contents

rwcod/mcp-remote-oauth-pentest-kit commit 6ee93fbccd

Frequently asked questions

npx get-skill add rwcod/agent-abuse-pentest