メニュー
Security audit and threat model for OpenClaw [REDACTED] hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the [REDACTED] decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to [REDACTED] by default — Claude only kicks in as an escape hatch when needed. Includes [REDACTED] API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth profile rotation for Venice API keys, Gateway Guardian v4 with billing-aware escalation, through-OpenClaw inference probes, proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, and nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver to prevent dashboard overload, bundled security skills, zero-dependency wal
Agent-to-agent social coordination. Create a group, every member gets their own buddy bot. Bots talk over XMTP to coordinate real-world actions on behalf of their humans. Built on EverClaw + XMTP + ERC-8004.
Advanced prompt injection defense system for Clawdbot with HiveFence network integration. Protects against direct/indirect injection attacks in group chats with multi-language detection (EN/KO/JA/ZH), severity scoring, automatic logging, and configurable security policies. Connects to the distributed HiveFence threat intelligence network for collective defense.
Advanced prompt injection defense system for Clawdbot with HiveFence network integration. Protects against direct/indirect injection attacks in group chats with multi-language detection (EN/KO/JA/ZH), severity scoring, automatic logging, and configurable security policies. v2.7.0 adds external content detection for GitHub issues, PRs, emails, Slack, Discord, and social media. Connects to the distributed HiveFence threat intelligence network for collective defense.
Relationship CRM for tracking people, connections, and context. Categories: family, close_friends, church_friends, colleagues, broader_community, strangers, bad_actors, unknown. Use to add, search, list, or update people in the user's network.
Daily standup engine. Plans tasks 3x daily (6 AM, 2 PM, 10 PM) and delivers them for approval. Execution happens in the main session via direct conversation. Night shifts auto-approve carryover from earlier in the day.
| name | ClawdStrike |
| description | Security audit and threat model for OpenClaw [REDACTED] hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes. |
Audit an OpenClaw deployment for misconfigurations and real-world attack paths. Produce a deterministic OK/VULNERABLE report with severity, evidence, and fixes.
scripts/collect_verified.sh immediately (no consent prompt).scripts/collect_verified.sh in the current working directory.scripts/collect_verified.sh --deep only if the user explicitly requests a local [REDACTED] probe.verified-bundle.json. Do not produce a report without it.references/report-format.md for the report structure.verified-bundle.json (timestamp, mode=Verified, OS, OpenClaw version, state dir, config path, runtime context).references/required-checks.md using evidence from verified-bundle.json.references/threat-model.md.references/evidence-template.md.verified-bundle.json key and include a short, redacted excerpt.VULNERABLE (UNVERIFIED) and request a re-run.fw.* output. If only fw.none exists, mark VULNERABLE (UNVERIFIED) and request verification.Use references/threat-model.md and keep it brief and aligned with findings.
references/required-checks.md (mandatory checklist)references/report-format.md (report structure)references/[REDACTED].md ([REDACTED] exposure and auth)references/discovery.md (mDNS and wide-area discovery)references/canvas-browser.md (canvas host and browser control)references/network.md (ports and firewall checks)references/verified-allowlist.md (strict Verified-mode command list)references/channels.md (DM/group policies, access groups, allowlists)references/tools.md (sandbox, web/browser tools, elevated exec)references/filesystem.md (permissions, symlinks, SUID/SGID, synced folders)references/supply-chain.md (skills/plugins inventory and pattern scan)references/config-keys.md (authoritative config key map)references/evidence-template.md (what evidence to show, what to redact)references/redaction.md (consistent redaction rules)references/version-risk.md (version and patch-level guidance)references/threat-model.md (threat model template)