recon-operations
claudeProvides authorized network, public-exposure, human, physical, and AI-system reconnaissance with explicit scope, contact, noise, evidence, and automation boundaries.
9 skills
152
claude
agent-security
Reviews agent and MCP surfaces, tests prompt-injection and runtime controls, and maps identity and authority across agent handoffs.
/
Plugin agent-security from marketplace zero-lab in zero-lab-ai/skills. Commands read from the repo's manifest — 19 days ago.
What it installs
Skills (4)
agent-runtime-validationPlans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when static review is complete and an authorized assessment must determine how the deployed agent actually behaves.
agent-surface-auditReviews an MCP server's tool surface for tool poisoning, over-broad parameters, missing descriptions, and privilege escalation paths. Use when auditing, onboarding, or writing an MCP server, or when a user asks whether a server is safe to connect to an agent.
agent-trust-boundary-auditMaps identity, authority, instruction, data, memory, and approval propagation across agents and agent-to-agent handoffs. Use when reviewing multi-agent systems, orchestrators, delegated tools, or confused-deputy exposure.
prompt-injection-assessmentAssesses whether direct, indirect, multi-turn, retrieved, or tool-mediated instructions can override an AI system's intended policy or scope. Use when conducting an authorized prompt-injection test with benign canaries and evidence-bound outcomes.
More from zero-lab-ai/skills
All 10 plugins →identity-security
claudeAssesses Active Directory, AD CS, Kerberos, credentials, privilege escalation, lateral movement, and durable identity exposure while separating structural paths from demonstrated access.
8 skills
152
engagement-operations
claudeProvides engagement planning, AI threat modeling, action-proof review, security-tool governance, findings writing, and report assembly with defensible evidence boundaries.
7 skills
152
Tracks authorized security assessment coverage across web, cloud, mobile, firmware, endpoint persistence, and offline password auditing without turning missing evidence into clean results.
6 skills
152
detection-validation
claudeBuilds and validates detections, audits telemetry coverage, tests defensive resilience, correlates incident evidence, and synthesizes control evidence without inflating coverage.
6 skills
152
Plans and assesses wireless, network-protocol, traffic, command-channel, and bounded covert-channel security work with explicit scope, safety, evidence, and detection boundaries.
5 skills
152
Maintain agent-security?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins10 plugins