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.
113 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.
Automated detection of IDOR vulnerabilities using a three-phase subagent workflow to verify authorization and ownership checks on sensitive endpoints.
Parses and processes SARIF files from static analysis tools. Enables aggregation, deduplication, filtering, and CI/CD integration of scan results.
Perform automated, rule-based performance and reliability audits for React and Next.js applications, covering bundle size, waterfalls, rendering, and data fetching.
AWS ECS skill for container orchestration. Manage clusters, task definitions, services, and deployments with best-practice patterns for Fargate and EC2.
Monitor Runwall security posture, enabled guardrails, and recent audit logs for Claude Code, Codex, and MCP-based development environments.
Audit outbound network requests and detect data exfiltration patterns in OpenClaw skills to ensure secure outbound communication.
Perform deep security analysis on codebases using CodeQL for interprocedural data flow, taint tracking, and automated vulnerability detection across multiple languages.
A runtime skill discovery engine for AI agents. Search and retrieve specialized agent skills (SKILL.md) on-demand via REST API or MCP to inject procedural knowledge into your agent's context.
Secure, isolated cloud sandbox environments for executing AI-generated code, running multi-language scripts, managing file systems, and integrating tools via the E2B MCP gateway.
Configure host-based firewalls (UFW, nftables, iptables) and cloud security groups (AWS, GCP, Azure) with production-ready security rules.
Conduct automated security assessments of WordPress sites using WPScan, enumeration techniques, and vulnerability scanning for themes, plugins, and users.