byshulkwisec· 58 skills
Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.
$npx -y skills add shulkwisec/bb-huge --skill ai-agent-tool-abuse-and-privilege-escalationInstalls into the current project.
Run `npx skills use "https://github.com/shulkwisec/bb-huge" --skill "shulkwisec/bb-huge/ai-agent-tool-abuse-and-privilege-escalation"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/shulkwisec/bb-huge" that are relevant to the current task. Run `npx skills add "https://github.com/shulkwisec/bb-huge"` and select the relevant skills, then follow their instructions.