Results for “technical-safeguards”

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

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

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

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

TypeScript Type Guards

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

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.

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

Detect sophisticated cyber-physical attacks that modify PLC logic while spoofing sensor readings, covering PLC integrity monitoring, process anomaly detection, and multi-stage attack chain detection.

Design and deploy IEC 62443-compliant conduit architecture for secure OT remote access, including jump servers, MFA gateways, session recording, and approval-based workflows for vendor and engineer access to industrial control systems.

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

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

AI safety and responsible AI practices

Deploys DNS, HTTP, and AWS API key canary tokens across network infrastructure to detect unauthorized access and lateral movement, with webhook alerting to Slack, Teams, email, or generic HTTP endpoints.

Conduct authorized physical penetration testing using tailgating, badge cloning, lock bypassing, and rogue device deployment to evaluate facility security controls.

Deploy and configure Tailscale as a WireGuard-based zero trust mesh VPN with identity-aware access controls, ACLs, and exit nodes for secure peer-to-peer connectivity.

Scan source code repositories, CI/CD pipelines, and configuration files for exposed AWS credentials using TruffleHog, git-secrets, and AWS-native detection mechanisms to prevent credential theft and unauthorized account access.

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.

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.

Conduct cybersecurity assessments for oil and gas facilities, covering upstream, midstream, and downstream operations, including SCADA, DCS, and safety systems, with compliance mapping to API 1164, TSA Pipeline Security Directives, IEC 62443, and NIST CSF.

Use this skill for auth boundaries, input validation, secrets, RLS, injection risks, destructive-action review. Trigger when the task involves security work related to Security Hardening, production implementation, audits, debugging, strategy, or validation.

Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.

Design leakage-safe feature engineering strategies for tabular/time-series datasets. Use when: (1) preparing model-ready features, (2) selecting transformations and encodings, (3) documenting feature lineage. NOT for: model serving or infra provisioning.

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

Dependency Safety Guards

Strict test-first gate only when explicitly requested or required by repository policy. Do not use for ordinary practical testing.

Consolidated engineering SOPs covering adapter development, TDD gating, and multi-agent operational protocols.

Assess cloud configuration risks including IAM privilege escalation, public storage exposure, network over-permissioning, and infrastructure-as-code misconfigurations.

Authorized OT/ICS security assessment covering Purdue model zoning, PLC/SCADA exposure, industrial protocol discovery, and safe passive-first evaluation.

Bash Pipeline Analysis

Internal technical readiness drill assistant for release and handoff.

Orchestrates VPN switching, geo-block diagnostics, and leak-aware task resumption by coordinating shell, curl, WireGuard, Tailscale, DNS, IPinfo, and MoltGuard skills.

Terraform infrastructure-as-code workflow patterns: state and environments, module design, safe plan/apply, drift control, and CI guardrails

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

Performs a full-stack security posture assessment with 0-100 risk scoring, scanning dependencies, code patterns, configuration, and data handling, then produces a prioritized report and routes to specialized skills.