Results for “safety-policy”

Review protected asset policy and risky local data surfaces.

Create, apply, and manage AgentRC policies to customize readiness scoring, disable checks, override impact levels, set pass-rate thresholds, and enforce CI gating.

Perform language and framework-specific security best-practice reviews, write secure-by-default code, and generate prioritized vulnerability reports with suggested fixes.

Apply Optionals, Protocols, Extensions, and Type Safety patterns in Swift. Use when working with Swift Optionals, Protocols, Extensions, or type-safe APIs.

Content Security Policy configuration, nonces, and reporting.

Use when a Supabase app needs Row Level Security policies for multi-tenant access, ownership checks, roles, service paths, or safe data exposure. Trigger on requests to design or review Supabase RLS and SQL authorization logic.

Restricts unauthorized removable media access on endpoints by implementing USB device control policies via Group Policy, Intune, or EDR platforms to prevent data exfiltration and malware introduction.

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.

AI safety and responsible AI practices

Automates security and compliance checks using OPA policies, Trivy vulnerability scanning, AWS CIS benchmark verification, and Kubernetes remediation scripts.

Implements Kubernetes network policies for micro-segmentation, covering ingress/egress rules, Calico and Cilium, with a Python CLI for managing and validating policies.

Hardens Windows Active Directory environments against ransomware by configuring Group Policy Objects with AppLocker rules, Controlled Folder Access, Attack Surface Reduction rules, and lateral movement restrictions.

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

Use to monitor support conversations for conduct risk — pressure, mis-selling, unfair outcomes, obstruction and misleading statements — as distinct from whether the answer matched policy. Trigger for "monitor for mis-selling", "conduct risk in our support conversations", "are agents pressuring customers", "customers being obstructed from cancelling", conduct surveillance, or a conduct finding raised by second line.

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

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

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.

Review governed memory proposals, policy tags, tombstones, and effective memory.

Local-first insurance record organizer for tracking policies, renewals, claims logs, and related insurance records. Use when the user wants to store policy details, list recorded policies, track renewal dates, log claim events, or summarize insurance records. NEVER provides insurance advice, recommends coverage amounts, or facilitates policy purchases.

OWASP Top 10 + Supabase-first hardening burndown. Use when "security audit plan", "OWASP audit", "hardening plan", or "security burndown". App-layer auth flows → audit-auth-flows. Table RLS → plan-rls-audit. Key rotation → plan-secrets-audit. App LLM attacks → audit-llm-security.

Write leave policies covering PTO, sick, and family leave. TRIGGERS - Use when user needs help with leave-policy related tasks.

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.

Continuously discover, classify, and score APIs based on risk while enforcing security policies across the API lifecycle.

Use with task-agent or review-agent for task-local cache scope, freshness, invalidation, and source-load risk. Do not use without a cache decision or as task owner.

Decide the highest-value safe thing to do right now in the active repo or workspace.

Guides reliable application deployment with CI/CD pipelines, zero-downtime strategies, rollback plans, and post-deploy monitoring.

Laravel 安全最佳实践，涵盖认证/授权、验证、CSRF、批量赋值、文件上传、密钥、速率限制和安全部署。

Use with analysis-agent, task-agent, or review-agent for task-local authentication lifecycle and recovery risk. Do not use without that decision or as task owner.

Generates HR policies for remote work, PTO, harassment prevention, and workplace safety compliance

Write leave policies covering PTO, sick, and family leave. TRIGGERS - Use when user needs help with leave-policy related tasks.

Applies C/C++ rules for resource safety, ownership, ABI, builds, tests, and validation.

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

Analyze and bypass Content Security Policy implementations to achieve cross-site scripting by exploiting misconfigurations, JSONP endpoints, unsafe directives, and policy injection techniques.