Results for “safetyculture”

Build a local browser agent that enforces a domain allowlist via CDP Fetch interception, using a safe_browser tool that owns the Playwright session and blocks off-domain requests.

Develop and implement OT-specific incident response playbooks aligned with SANS PICERL framework, IEC 62443, and NIST SP 800-82 that address unique ICS challenges including safety-critical systems, limited downtime tolerance, and coordination between IT SOC, OT engineering, and plant operations teams.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Enforces bulk-safety rules, sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage, and modern Apex idioms for Salesforce development.

Manage production secret infrastructure with HashiCorp Vault, cloud secret stores, automated rotation, and audit logging.

Secure Laravel applications with best practices for authentication, authorization, Eloquent safety, CSRF, XSS prevention, API security, and deployment configurations.

Use this skill when the user asks how to build, measure, or improve safety culture in a motor carrier — leading vs lagging safety indicators, blame-free reporting, near-miss programs, safety committee structure, monthly safety meetings, ATA Safety Management Program guidance, and how to evaluate cultural maturity. Reference ATA SMP + DOT safety culture research.

Configure and execute access recertification campaigns in Saviynt Enterprise Identity Cloud to validate user entitlements, revoke excessive access, and maintain compliance with SOX, SOC2, and HIPAA.

Designs and documents structured incident response playbooks aligned with NIST SP 800-61r3 and SANS PICERL frameworks, covering playbook structure, decision trees, escalation criteria, RACI matrices, and SOAR integration.

Triages security incidents by classifying type, assigning severity based on business impact, enriching with threat intelligence, and routing to appropriate response teams using NIST SP 800-61r3 and SANS PICERL frameworks.

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

Implements or verifies the six-layer type safety chain from Drizzle schema through Zod, services, API routes, and React hooks, including regeneration after DB changes and bootstrapping in new folders.

Routes security, compliance, and threat-intelligence tasks to specialized sub-skills for threat modeling, penetration testing, incident response, and vulnerability scanning.

AI safety and responsible AI practices

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".

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

Validates, tests, and scores the quality of skills within a claude-skills ecosystem using Python scripts that check structure, syntax, runtime, and multi-dimensional quality metrics.

Audit Claude Code configuration files for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

Facilitates discussion-based tabletop exercises for SOC teams to test incident response procedures, communication workflows, and decision-making under pressure without impacting production systems.

Deliberately disables or degrades security controls to verify detection and response capabilities, including WAF bypass, firewall rule removal, log pipeline disruption, and EDR disablement scenarios using boto3 and subprocess.

Pre-install security scanner for AI agent skills. 7.5% of 14,706 skills are malicious. Audit before you trust.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

Turn an at-risk account into a churn-save play. It diagnoses the real reason behind the risk (not the stated one), lays out the commercial and non-commercial levers you can pull, and builds a multi-touch save sequence with owners and dates. Built for B2B customer success teams, customizable to your CRM and product analytics. Trigger on "this account is going to churn", "build a save play", "why are they leaving", "at-risk renewal", "how do I keep this account", or any retention rescue.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Security Craft

Audit/harden MarketingClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Content Security Policy configuration, nonces, and reporting.

Provides a comprehensive security checklist and code patterns for authentication, input validation, secrets management, SQL injection prevention, XSS, CSRF, rate limiting, and sensitive data exposure.

Design Security Operations Centers with processes. TRIGGERS - Use when user needs help with soc-design related tasks.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Detect authentication attacks, privilege escalation, persistence mechanisms, and lateral movement by analyzing Windows Security, System, and Sysmon event logs in Splunk using SPL queries mapped to MITRE ATT&CK techniques.

Provides a structured 5-phase workflow for bug bounty and SRC vulnerability hunting, including 19 attack-type playbooks, 305 structured payloads, 263 WAF bypass variants, and 2,887 real HackerOne case studies.

Access 31 pay-per-use tools for quantum security, agent safety, research, data, and earn on Base, paid via x402 protocol.

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