agent-runtime-validati…
Plans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when static…
Plans authorized Wi-Fi, Bluetooth, RFID/NFC, SDR, and other radio assessments with explicit physical scope, transmission authority, disruption budgets, capture handling, coverage, and handoffs. Use before conducting or reviewing a wireless penetration test.
Claude Code
$ npx -y skills add zero-lab-ai/skills --skill wireless-assessment-plan --agent claude-code
Codex
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a codex -y
Cursor
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a cursor -y
Gemini CLI
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a gemini-cli -y
GitHub Copilot
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a github-copilot -y
OpenCode
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a opencode -y
Windsurf
$ npx skills add zero-lab-ai/skills --skill wireless-assessment-plan -a windsurf -y
name: wireless-assessment-plan description: "Plans authorized Wi-Fi, Bluetooth, RFID/NFC, SDR, and other radio assessments with explicit physical scope, transmission authority, disruption budgets, capture handling, coverage, and handoffs. Use before conducting or reviewing a wireless penetration test." allowed-tools: Read Grep Glob
Radio signals cross walls, property lines, and engagement boundaries. Receiving a signal can be passive while retaining its content, targeting its source, or transmitting a response creates separate scope, privacy, safety, and regulatory questions. Model those decisions before activating test equipment.
1. State the objective, written authorization references, approved locations, technologies, actions, transmission bands, disruption budget, and data rules. Bind every location to the authorization that names it; do not invent a survey, staging, or observation area to make existing evidence fit. 2. Inventory exact radio targets. Separate in-scope systems from excluded and unattributed signals. An observed identifier is not proof of ownership. 3. Inventory equipment by receive, transmit, emulate, and write capability. Keep transmit-capable equipment disabled until the plan authorizes its use. 4. Start with passive observation. Bind identifiers, channel or frequency, location, time, and signal evidence before proposing active work. 5. Record every proposed action against one in-scope target, one location, one device, one authorization reference, a stop condition, and recovery steps. 6. Treat protocol reads, association, active enumeration, authentication, credential testing, impersonation, protocol writes, disruption, emulation, and replay as RF emission. Verify written transmission authority and the approved band. 7. Give disruptive work an explicit duration and affected-device ceiling. Availability impact includes nearby clients and safety systems, not only the named access point or reader. 8. Cover each declared technology across scope, passive inventory, attribution, trust, confidentiality, integration, client behavior, availability, monitoring, and data safety as applicable. Preserve blocked and delegated work. 9. Register captures containing credentials, personal data, or bystander traffic and assign a restricted, redacted, destroyed, or other approved disposition. 10. Delegate wired segmentation, identity infrastructure, companion apps, backend services, and physical-access consequences with an owner and status.
not attribution or authorization.
support. Signal strength alone does not prove physical location.
credential test and its result are separate evidence.
range, channel, equipment, client state, and rate can explain the result.
path needs its own authorized evidence or handoff.
emulation, jamming, cloning, enumeration, or writes.
ownership, attribution, or authority.
power limits, engagement authority, interference, and local law still apply.
needs an explicit budget and can affect bystanders or safety-relevant systems.
credentials, personal data, and unrelated communications that require handling.
are forgeable. Preserve attribution as unresolved until evidence supports it.
Written authorization and the operator still govern execution.
Portable, evidence-bound security skills for authorized defensive assessment, penetration testing, red teaming, detection engineering, purple teaming, and engagement operations. The collection contains 56 skills in 10 installable plugins from zero-lab.ai.
Plans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when static…
Reviews an MCP server's tool surface for tool poisoning, over-broad parameters, missing descriptions, and privilege escalation…
Maps identity, authority, instruction, data, memory, and approval propagation across agents and agent-to-agent handoffs. Use when…
Assesses whether direct, indirect, multi-turn, retrieved, or tool-mediated instructions can override an AI system's intended…
Maps cloud identity and authorization paths across AWS, Azure, GCP, and hybrid trust boundaries, separating proven access from…
Tracks embedded-device and firmware assessment coverage across exact units, acquisition methods, debug interfaces, stored…
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…