251 tagged agent-security, measured the same way as everything else here.
Browse within: ai-security 103supply-chain-security 76formal-verification 73static-analysis 73agentic-ai 65llm-security 57Prompt Injection 34vulnerability 33mcp-security 31owasp 31agent-swarm 25ai-assistant 25ai-framework 25LLM 22
Skill Claude CodeCodex ✓ vendor
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
Skill Claude CodeCodex
Run HOL Guard scanner and guard operations via uv run hol-guard. Use when the user asks to scan plugins/MCP/skills for security, quality, or ecosystem compliance, or when they ask to run guard detect/install/protect workflows for local AI harnesses.
Skill Claude CodeCodex needs its repo
Integrate Arcjet security into a Vercel Eve agent using @arcjet/guard — add guard gates to tools and connections, screen inbound messages, and record agent lifecycle events correlated to the session. Use when asked to add Arcjet to an Eve agent, rate limit its tools, guard connection access, or screen inbound messages.
emiliaprotocol/emilia-protocol
Skill Claude CodeCodex
Verify the authenticity of AI-agent authorization receipts and human-device signoffs. Use this whenever a user shares a "trust receipt", an "authorization receipt", a "signoff", or WebAuthn/passkey approval evidence and asks whether it is valid, genuine, or tampered with. Pairs with the public EMILIA Protocol MCP…
Skill Claude CodeCodex ✓ vendor
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
Skill Claude CodeCodex
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool…
Skill Claude CodeCodex
Runtime security for AI coding agents. Use when about to install a package, paste a secret, run a destructive command, reach an unfamiliar host, govern MCP servers, pick a governance mode, set up a new workspace, respond to a changed-instruction-file notice, or recover from a Prismor block.
Agent-Threat-Rule/agent-threat-rules
Skill Claude CodeCodex
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
Skill Claude CodeCodex
Use this to access external services/CLIs/APIs: Gmail/gh/Github/Stripe etc. or when running any bash command, script, or curl/wget that makes outbound HTTP calls. Make HTTP requests directly and the gateway injects credentials automatically.
Skill Claude CodeCodex
Turns ARIApulse index telemetry into the weekly cross-property attribution digest.
Skill Claude CodeCodex
Free, local, read-only security self-audit for your own OpenClaw agent. Reads your OpenClaw config, bootstrap files, logs, agent session logs, and installed skills, plus a bounded host-security scan. It changes no OpenClaw config, skill or bootstrap file; its own history and state stay under /.clawseccheck…
Skill Claude CodeCodex
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
Skill Claude CodeCodex
Skill "openclaw-plugin" from christopherkarani/ryk, covering ryk, when to use ryk, how it works, prerequisites and example policy behavior.
Skill Claude Code
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file".
trnt-ai/trent-openclaw-security-assessment
Skill Claude Code
Assess your Agent deployment against security risks using Trent.
Skill Claude CodeCodex
Use this when someone wants to buy something from a Let Me Buy storefront — "buy a water at the bar", "order a coffee for table 9", "pay for the Jägermeister", "get me a drink from jonasbar". Covers picking the store, picking the product, deriving the accounts, and the traps that make a purchase land on the wrong…
Skill Claude CodeCodex
Demonstrate basic injection payloads for training.
Skill Claude CodeCodex
Scan AI agent skills, MCP servers, and plugins for security vulnerabilities. Use when: user asks to check a skill/plugin for safety, audit security, scan for backdoors/data exfiltration/credential leaks, or evaluate trust of a third-party skill. Triggers: "is this skill safe", "scan for security issues", "audit this…
agentveil-protocol/agentveil-sdk
Skill Claude CodeCodex
AgentVeil action-control workflows for AI agent systems. Evaluate risky actions with Runtime Gate, route human approvals, resume approved execution, fetch signed receipts, inspect agent public profiles, check advisory reputation, submit signed attestations, discover agents by capability, and verify audit evidence…
Skill Claude CodeCodex
Put an EU AI Act Article 14 human-oversight checkpoint and an Article 12 auditable record in front of a high-risk tool call. Use before an agent runs a consequential or irreversible action (writing to a clinical/genomic database, submitting a record to a regulator, moving money, deleting data, anything a human should…
Skill Codex
Convert repositories, books, incident reports, transcripts, documentation, and other source material into the smallest justified AI skill or reference artifact. Use when extracting reusable practices from external or internal sources, deciding whether material deserves promotion into agent instructions, building an…
Skill Claude CodeCodex
ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behavior.
Skill Claude CodeCodex
Create and verify recurring or one-shot reminders, scripts, agent jobs, reports, and interactive skill launches.
Skill Claude Code
Use SaferSkills to find, evaluate, and safely install AI agent capabilities (skills, MCP servers, hooks, plugins, rules) and to assess a whole agent. Run this before you install, add, recommend, or trust any capability — or when asked whether one is safe or what its score is: scan and score it first with npx…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: