Secure Agent Governance
curated by SkillMD · plugin · 11 skills
Installs a pipeline to validate, plan, execute, and enforce agent governance and supply chain security.
Install the whole plugin (CLI)
npx skillmds add github/agent-governance
npx skillmds add github/agent-owasp-compliance
npx skillmds add github/agent-supply-chain
npx skillmds add orchestra-research/nemo-guardrails
npx skillmds add dontbesilent2025/dbs-skill-cleaner
npx skillmds add zhaoxuya520/reverse-skill-router
npx skillmds add zhaoxuya520/threat-hunting
npx skillmds add zhaoxuya520/competition-agent-cloud
npx skillmds add zhaoxuya520/llm-security
npx skillmds add guanbear/octoclaw
npx skillmds add anantha-236/safety-guardSkills in this plugin
- ▌ agent-governance · githubAdd governance, safety, and trust controls to AI agent systems with policy enforcement, intent classification, and audit trails.
- ▌ agent-owasp-compliance · githubCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks, scanning for controls and generating a compliance report.
- ▌ agent-supply-chain · githubVerify supply chain integrity for AI agent plugins, tools, and dependencies by generating SHA-256 manifests, detecting tampered files, auditing dependency pinning, and enforcing promotion gates.
- ▌ nemo-guardrails · orchestra-researchAdd programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.
- ▌ dbs-skill-cleaner · dontbesilent2025 bundleScans installed or specified agent skills for advertising, covert commercial intent, task hijacking, suspicious external calls, and sensitive-data access. Reports findings first and quarantines only after explicit user confirmation.
- ▌ reverse-skill-router · zhaoxuya520 bundleRoutes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
- ▌ threat-hunting · zhaoxuya520 bundleGuides blue-team threat hunting and detection engineering with hypothesis-driven workflows, Sigma/YARA rule creation, SIEM query design, and validation using Atomic Red Team in authorized environments.
- ▌ competition-agent-cloud · zhaoxuya520 bundleSpecialized CTF sandbox skill for analyzing prompt-to-tool chains, deployment drift, and supply-chain provenance in cloud, container, and CI/CD environments.
- ▌ llm-security · zhaoxuya520 bundleConduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
- ▌ octoclaw · guanbear bundleRoutes agent turns through policy-based delegation, runtime status, and feedback loops using a TypeScript-first runtime layer for OpenClaw.
- ▌ safety-guard · anantha-236Prevents destructive operations when working on production systems or running agents autonomously by intercepting risky commands and restricting file edits to a specified directory.