Results for “guardian-sensor”

Use when tenant data protection, data privacy compliance, data encryption, or data governance is needed. This agent specializes in SaaS data protection within the SaaSForge AI ecosystem.

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure actions.

Resolves legacy references to the security-guardian capability by routing to the current runtime equivalent.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

Configure, simulate, debug, and analyze radarDataGenerator within radarScenario. Use for: interactively building radar detection scenarios from datasheets or performance requirements; diagnosing missed detections and configuration errors; interpreting sensor spherical, body, and scenario-frame outputs; deriving ReferenceRange from hardware specs via link budget; scan mode configuration (mechanical, electronic/AESA, hybrid); and validating simulation results against analytical predictions.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.

Guides implementing authentication, authorization, input validation, and OWASP Top 10 prevention with secure code patterns and validation checkpoints.

Watches a Gmail mailbox for new emails and streams them as NDJSON, with options for Pub/Sub setup, filtering by labels, and output to files.

Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy. Use when PR preparation or commit strategy is needed.

BISON v2.0 — Conviction Holder (Hardened). Top 10 assets by volume. All signals are score contributors — no hard gates. Scanner enters via create_position internally (Wolverine pattern). RatchetStop exits. Thesis exit REMOVED. v2.0: every hard gate converted to score contributor, ensureExecutionAsTaker=false, conviction-scaled margin 25-37%.

Provides a framework for proactive health monitoring and optimization, treating the human body as an asset to be maintained through telemetry, diagnostics, and interventions.

Deploy and operationalize Amazon GuardDuty for continuous threat detection across AWS accounts and workloads, including enabling protection plans, interpreting findings, and building automated response workflows.

Adds input and output guardrails to an agent, including validation, content filtering, domain scoping, and rate limiting, with TypeScript examples and wiring instructions.

Apply a jq-style filter to transform a JSON payload

Keeps long AI sessions on track by tracking decisions, detecting scope creep, and flagging drift before it costs work.

AI security and safety specialist for guardrails and adversarial resilience. Use when the user asks to talk to Snape, requests a safety audit, or needs guardrails design.

Scan container images for known vulnerabilities using Anchore Grype with SBOM-based matching and configurable severity thresholds.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

Automate AWS GuardDuty threat detection findings processing using EventBridge and Lambda to enable real-time incident response, automatic quarantine of compromised resources, and security notification workflows.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Retrieve a value by key from the Custodian KV store

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Gather fresh frontier signals for AI agent infrastructure, Vue, and Vite from live public feeds before producing summaries or strategic analysis.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Scan agent skills for security issues before adoption. Detects prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks.

AI safety and responsible AI practices

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

VIXEN v1.0 — Dual-mode emerging movers scanner. Built from FOX v1.6 live trading data (+34.5% ROI). Two entry modes: STALKER (steady accumulation, score 6+, catches the SM buildup BEFORE the explosion) and STRIKER (violent FIRST_JUMP, score 9+, with raw volume confirmation to filter blow-off tops). 2-hour per-asset cooldown after Phase 1 exits. DSL High Water Mode mandatory.

Filters user-generated content for safety using Google Model Armor via the gws CLI.