indirect-injection-detection
Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
300 skills found
Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.
A comprehensive toolkit for measuring, auditing, and debugging web performance metrics including Core Web Vitals, loading speed, and interaction latency directly in Chrome DevTools.
Replaces arbitrary test timeouts with robust condition-based polling to eliminate flaky tests, race conditions, and timing-dependent failures in software testing suites.
Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.
Test web applications with screen readers like VoiceOver, NVDA, and JAWS. Validate accessibility, debug assistive technology issues, and ensure compliance with screen reader support standards.
Monitor Runwall security posture, enabled guardrails, and recent audit logs for Claude Code, Codex, and MCP-based development environments.
Evaluate scientific claims and research methodology for rigor, bias, and validity. Use evidence-based frameworks like GRADE and Cochrane to analyze experiments, protocols, and study conclusions.
Synthesizes multi-agent research findings into coherent, citation-backed reports, resolving contradictions and identifying consensus.
Reference for all MCP tools exposed by the CCOS server, enabling capability discovery, session management, and governed RTFS execution for autonomous agent workflows.
Enforces disciplined Test-Driven Development (TDD) by requiring a failing test before implementation, ensuring code reliability and preventing premature over-engineering.
Analyze UI/UX quality against 4 authoritative standards (NNg, Laws of UX, Apple HIG, WCAG) to receive actionable design and accessibility improvements for mobile and web components.
Streamline technical documentation for BattleScope features, maintaining consistency across API, frontend, and architecture layers.