1K skills · sorted by relevance
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
Set up WireGuard remote access to a home network from phones and laptops. Covers server configuration, device keys, troubleshooting, and choosing whether only home network traffic or all internet traffic passes through the VPN.
Build safety checks for LLM prompts and responses using Meta's LlamaGuard moderation model. Classify potentially harmful content, block flagged messages, serve checks through an API, and integrate them with NeMo Guardrails.
Manage AdGuard Home network filtering from the command line. Update blocklists, register devices, configure DNS rules that map names to addresses, and inspect query logs and statistics through the AdGuard Home REST API.
Build automated responses to AWS GuardDuty security findings using EventBridge and Lambda. Configure severity filters, isolate EC2 instances, disable compromised access keys, preserve disk snapshots for investigation, and send notifications to security teams.
Build safety checks for LLM prompts and responses using Meta's LlamaGuard. This skill covers content classification, batch moderation, serving a moderation API, and connecting checks to NeMo Guardrails.
Adds checks before an agent runs destructive commands and restricts file edits to a chosen directory. Offers separate or combined protection modes for production work, autonomous sessions, migrations, deployments, and data changes.
Set up and operate Amazon GuardDuty to detect threats in AWS. Configure protection features, centralize findings across accounts, investigate suspicious activity, and build automated responses with EventBridge and Lambda, including containment of potentially compromised resources.
Detect unauthorized cryptocurrency mining in cloud workloads by combining billing changes, CPU usage, mining pool connections, and process alerts. Follow workflows to preserve evidence, isolate affected resources, and trace how attackers gained access.
Build a screening pipeline for web pages, PDFs, and images before an AI agent reads them. Extract hidden text, check for malicious instructions with detection models, and record decisions to block or allow content.
Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.
The English summary is being prepared. Showing the original description.
Investigate suspected data theft from AWS S3 by comparing access logs, GuardDuty findings, and Macie classifications. Identify unusual bulk downloads and transfers across accounts, assess sensitive data exposure, and build automated detection rules.
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...
The English summary is being prepared. Showing the original description.
Inspect npm packages and dependency files for malicious installation scripts, credential theft, and self-spreading behavior. Use GuardDog scanning, source inspection, known-malicious version checks, and isolated execution to produce an evidence-based assessment.
Submit security scans for AI services, tools, skills, and agents through AI-Infra-Guard, then retrieve progress and results. It also supports jailbreak evaluation, testing whether prompts can bypass a model’s safety restrictions.
Configure a Claude hook, a check before tool execution, that pauses initial edits and file creation to request concrete facts. It prompts investigation of callers, data structures, and user instructions, with separate checks for destructive commands.
Plan and review home network changes before altering settings. The skill checks VLANs, which separate device groups, local DNS filtering, and VPN access, then organizes staged changes, validation checks, and recovery steps.
Set up encrypted connections between devices with Tailscale and control access by user or device. The skill covers network routing, device name resolution, and self-hosting the coordination server with Headscale.
Inspect suspicious Android APK files without running them. Analyze permissions, app components, suspicious code patterns, and network indicators, then produce a JSON risk report to support malware triage and detection rule development.
Helps configure and troubleshoot Linux networks, including firewalls, routing, and DNS, which translates domain names into addresses. Covers traffic capture, isolated test networks, WireGuard VPN setup, and TCP tuning across physical servers, virtual machines, and containers.
Analyze and enforce repository, runtime, data, spend, endpoint, and approval guardrails without guessing secret formats or content-policy rules. Use when the task requires adobe policy and execution guardrails. Trigger with "Adobe guardrails", "block unsafe Adobe calls", or "Adobe policy checks".
The English summary is being prepared. Showing the original description.
How AgentGuards enforces its guardrails in Codex — fully automatic, via hooks, with nothing for you to call. Load this if asked how AgentGuards works, whether you need to screen something yourself, or why no agentguards check_input / authorize_action tools are available.
The English summary is being prepared. Showing the original description.