Results for “safety-guard”

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Add safety guardrails to an LLM app — prompt-injection defense, output validation, PII handling, and a clear refusal policy.

AI Safety Specialist IA — Expert en sécurité IA (alignment, guardrails, filtrage de contenu, test de biais, red teaming)

Add programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

Prevents destructive operations when working on production systems or running agents autonomously by intercepting risky commands and restricting file edits to a specified directory.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Create and manage a Twitter/X agent with a persistent personality, automated posting workflows, and safety guardrails.

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

Implements advanced TypeScript type systems, creates custom type guards, utility types, and branded types, and configures tRPC for end-to-end type safety.

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

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors.

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.

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

AI safety and responsible AI practices

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.

Guardian of V.A.I.R.E. quality standards (Value/Agency/Identity/Resilience/Echo). Handles pre-release evaluation, scorecard assessment, and pass/fail determination. Use when UX quality gates are needed. Does not write code.

TypeScript Type Guards

Generates creative launch blueprints for memecoins on pump.fun, including names, symbols, narratives, and buyback plans, with built-in safety guardrails.

Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.

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.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Configure email security gateways like Microsoft Defender, Proofpoint, and Mimecast to detect and block targeted spearphishing attacks using impersonation protection, URL detonation, and attachment sandboxing.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

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.

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