Review Ai Agent Surface banner
sourjya sourjya

Review Ai Agent Surface

Security community

Description

--- description: "Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and unsafe handling of model output. Produces an AISR report." --- <!-- ============================================================================= review-ai-agent-surface.md - AI / agentic feature security audit prompt ============================================================================= FRAMEWORK PROVENANCE This prompt's objectives and severity model are derived

Installation

Installs to ~/.claude/commands/sourjya-kiro-rails-review-ai-agent-surface.md

Terminal
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/sourjya/kiro-rails/HEAD/.claude/commands/review-ai-agent-surface.md -o ~/.claude/commands/sourjya-kiro-rails-review-ai-agent-surface.md

Restart Claude Code, or start a new session, for it to be picked up.

Full documentation available on GitHub

View Source Repository