Results for “ai-safety”

Add governance, safety, and trust controls to AI agent systems with policy enforcement, intent classification, and audit trails.

Configure Azure API Management as an AI Gateway to govern AI models, MCP tools, and agents with policies for caching, rate limiting, content safety, and cost control.

Enforces evidence-based debugging, safety gates, and anti-slack detection to keep AI agents thorough and honest during code changes.

Analyze text and images for harmful content using Azure AI Content Safety, with customizable blocklists and severity thresholds.

Enforces safety gates, evidence-based debugging, anti-slack detection, and verification hooks when AI modifies files, configs, or deployments.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Enforces a six-layer governance framework for AI agents: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks to ensure safe, thorough, and honest 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.

tRPC end-to-end type safety, procedures, routers, middleware, and React integration.

Analyze text and images for harmful content using Azure AI Content Safety SDK for Java. Supports hate, violence, sexual content, and self-harm detection with blocklist management.

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

Scan and audit AI agent skills for security risks before installation, producing a PASS/WARN/FAIL verdict with findings and remediation guidance.

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Security engineer skill for backend ACL structure, menu visibility control, and administrative access safety.

Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs covering discovery, authentication, authorization, rate-limiting, and CI/CD integration.

Assistant for newapi (new-api), an open-source unified AI gateway platform (https://github.com/QuantumNous/new-api). Use when the user asks about New API, managing models, groups, balance, or tokens, or securely copying keys, applying them to config files, or using them in commands without exposing secrets.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

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

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Expert guidance on secure coding practices, focusing on preventing common security errors made by AI during code generation. Use for: auditing AI-generated code, implementing secure design patterns, and ensuring code follows OWASP Top 10 standards. Covers input validation, authentication, cryptography, file handling, secure configuration, and business logic security.

Governs AI coding agents with safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks to ensure safe, thorough, and honest work.

AI Manipulation Defense System with self-learning prompt injection detection and adaptive mitigation

Safety guardrails for autonomous agents. Intercepts destructive actions and vets skills, requires structured approval before irreversible operations, with CLI-backed cryptographic audit trails and policy enforcement.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes in API designs, configuration schemas, and cryptographic library ergonomics.

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks, scanning for controls and generating a compliance report.

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.